An international competition for negotiating agents has been organized for years to facilitate research in agent-based negotiation and to encourage the design of negotiating agents that can operate in various scenarios. The 13th International Automated Negotiating Agents Competition (ANAC 2022) was held in conjunction with IJCAI2022. In ANAC2022, we had two leagues: Automated Negotiation League (ANL) and Supply Chain Management League (SCML). For the ANL, the participants designed a negotiation agent that can learn from the previous bilateral negotiation sessions it was involved in. In contrast, the research challenge was to make the right decisions to maximize the overall profit in a supply chain environment, such as determining with whom and when to negotiate. This chapter describes the overview of ANL and SCML in ANAC2022, and reports the results of each league, respectively.

@inproceedings{ANAC2022,
  author = {Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Fujita, Katsuhide and Hoos, Holger H. and Jonker, Catholijn M. and Mohammad, Yasser and Renting, Bram M.},
  title = {The 13th International Automated Negotiating Agent Competition Challenges and Results},
  booktitle = {Recent Advances in Agent-Based Negotiation: Applications and Competition Challenges},
  publisher = {Springer Nature Singapore},
  year = {2023},
  pages = {87--101},
  address = {Singapore},
  editor = {Hadfi, Rafik and Aydoğan, Reyhan and Ito, Takayuki and Arisaka, Ryuta}
}

This work presents several new and efficient algorithms that can be used by negotiating agents to explore very large outcome spaces. The proposed algorithms can search for bids close to a utility target or above a utility threshold, and for win-win outcomes. While doing so, these algorithms strike a careful balance between being rapid, accurate, diverse, and scalable, allowing agents to explore spaces with as many as 10^250 possible outcomes on very run-of-the-mill hardware. We show that our methods can be used to respond to the most common search queries employed by 87 percent of all agents from the Automated Negotiating Agents Competition between 2010 and 2021. Furthermore, we integrate our techniques into negotiation platform GeniusWeb in order to enable existing state-of-the-art agents (and future agents) to handle very large outcome spaces.

@article{BIDSjournal,
  author = {Ko{\c{c}}a, Thimjo and de Jonge, Dave and Baarslag, Tim},
  title = {Search algorithms for automated negotiation in large domains},
  journal = {Annals of Mathematics and Artificial Intelligence},
  month = {July},
  year = {2023},
  issn = {1573-7470},
  url = {https://doi.org/10.1007/s10472-023-09859-w},  
  doi = {10.1007/s10472-023-09859-w}
}

Many service providers require permissions to access privacy-sensitive data that are not necessary for their core functionality. To support users’ privacy management, we propose a novel agent-based negotiation framework to negotiate privacy permissions between users and service providers using a new multi-issue alternating-offer protocol based on exchanges of partial and complete offers. Additionally, we introduce a novel approach to learning users’ preferences in negotiation and present two variants of this approach: one variant personalised to each individual user, and one personalised depending on the user’s privacy type. To evaluate them, we perform a user study with participants, using an experimental tool installed on the participants’ mobile devices. We compare the take-it-or-leave-it approach, in which users are required to accept all permissions requested by a service, to negotiation, which respects their preferences. Our results show that users share personal data 2.5 times more often when they are able to negotiate while maintaining the same level of decision regret. Moreover, negotiation can be less mentally demanding than the take-it-or-leave-it approach and it allows users to align their privacy choices with their preferences. Finally, our findings provide insight into users’ data sharing strategies to guide the future of automated and negotiable privacy management mechanisms.

@article{PrivacyNegotiations,
  author = {Filipczuk, Dorota and Baarslag, Tim and Gerding, Enrico H. and schraefel, m. c.},
  title = {Automated privacy negotiations with preference uncertainty},
  journal = {Autonomous Agents and Multi-Agent Systems},
  publisher = {Springer},
  month = {August},
  year = {2022},
  volume = {36},
  pages = {1--38},
  issn = {1573-7454},
  url = {https://doi.org/10.1007/s10458-022-09579-1},  
  doi = {10.1007/s10458-022-09579-1}
}

This work presents BIDS (Bidding using Diversified Search), an algorithm that can be used by negotiating agents to search very large outcome spaces. BIDS provides a balance between being rapid, accurate, diverse, and scalable search, allowing agents to search spaces with as many as 10^250 possible outcomes on very run-of-the-mill hardware. We show that our algorithm can be used to respond to the three most common search queries employed by 87{\%} of all agents from the Automated Negotiating Agents Competition. Furthermore, we validate one of our techniques by integrating it into negotiation platform GeniusWeb, to enable existing state-of-the-art agents (and future agents) to scale their use to very large outcome spaces.

@inproceedings{BIDS,
  author = {Ko{\c{c}}a, Thimjo and Jonker, Catholijn M. and Baarslag, Tim},
  title = {Enabling Negotiating Agents to Explore Very Large Outcome Spaces},
  booktitle = {Autonomous Agents and Multiagent Systems. Best and Visionary Papers},
  publisher = {Springer International Publishing},
  year = {2022},
  pages = {67--83},
  address = {Cham},
  editor = {Melo, Francisco S. and Fang, Fei},
  url = {https://link.springer.com/chapter/10.1007/978-3-031-20179-0_4}
}

Computers that negotiate on our behalf hold great promise for the future and will even become indispensable in emerging application domains such as the smart grid and the Internet of Things. Much research has thus been expended to create agents that are able to negotiate in an abundance of circumstances. However, up until now, truly autonomous negotiators have rarely been deployed in real-world applications. This paper sizes up current negotiating agents and explores a number of technological, societal and ethical challenges that autonomous negotiation systems have brought about. The questions we address are: in what sense are these systems autonomous, what has been holding back their further proliferation, and is their spread something we should encourage? We relate the automated negotiation research agenda to dimensions of autonomy and distill three major themes that we believe will propel autonomous negotiation forward: accurate representation, longterm perspective, and user trust. We argue these orthogonal research directions need to be aligned and advanced in unison to sustain tangible progress in the field.

@inbook{BaarslagChallengesBook,
  author = {Baarslag, Tim and Kaisers, Michael and Gerding, Enrico H. and Jonker, Catholijn M. and Gratch, Jonathan},
  title = {Self-sufficient, Self-directed, and Interdependent Negotiation Systems: A Roadmap Toward Autonomous Negotiation Agents},
  booktitle = {Bargaining: Current Research and Future Directions},
  publisher = {Springer International Publishing},
  year = {2022},
  pages = {387--406},
  address = {Cham},
  editor = {Karagözoğlu, Emin and Hyndman, Kyle B.},
  url = {https://doi.org/10.1007/978-3-030-76666-5_18},  
  doi = {10.1007/978-3-030-76666-5_18}
}

This work presents the Autonomous Bidding and Coordinated Acceptance framework (ABCA): an agent-team design that allows general bilateral agents to engage in one-to-many negotiations in a setting where (possibly overlapping) deals with multiple opponents are desirable. We propose also a coordinated acceptance strategy that uses the estimated outcomes of its bilateral negotiations while deciding to accept a deal.

@inproceedings{ABCA,
  author = {Ko\c{c}a, Thimjo and Baarslag, Tim and Jonker, Catholijn M.},
  title = {Autonomous Bidding & Coordinated Acceptance in One-to-Many Negotiations},
  booktitle = {2021 IEEE International Conference on Agents (ICA)},
  year = {2021},
  pages = {31--36},  
  doi = {10.1109/ICA54137.2021.00012}
}

@inproceedings{Mag21,
  author = {Adel Magra and Peter Spreij and Tim Baarslag and Michael Kaisers},
  title = {Automated Negotiation Under User Preference Uncertainty},
  booktitle = {Proceedings of the 2021 Benelux Conference on Artificial Intelligence},
  year = {2021}
}

This study presents Bargaining Chips: a framework for one-to-many concurrent composite negotiations, where multiple deals can be reached and combined. Our framework is designed to mirror the salient aspects of real-life procurement and trading scenarios, in which a buyer seeks to acquire a number of items from different sellers at the same time. To do so, the buyer needs to successfully perform multiple concurrent bilateral negotiations as well as coordinate the composite outcome resulting from each interdependent negotiation. This paper contributes to the state of the art by: (1) presenting a model and test-bed for addressing such challenges; (2) by proposing a new, asynchronous interaction protocol for coordinating concurrent negotiation threads; and (3) by providing classes of multi-deal coordinators that are able to navigate this new one-to-many multi-deal setting. We show that Bargaining Chips can be used to evaluate general asynchronous negotiation and coordination strategies in a setting that generalizes over a number of existing negotiation approaches.

@inproceedings{BaarslagBargainingChips,
  author = {Baarslag, Tim and Elfrink, Tijmen and Nassiri Mofakham, Faria and Ko\c{c}a, Thimjo and Kaisers, Michael and Aydogan, Reyhan},
  title = {Bargaining Chips: Coordinating One-to-Many Concurrent Composite Negotiations},
  booktitle = {IEEE/WIC/ACM International Conference on Web Intelligence},
  publisher = {Association for Computing Machinery},
  year = {2021},
  pages = {390–397},  
  series = {WI-IAT '21},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3486622.3494023},  
  doi = {10.1145/3486622.3494023},
  keywords = {composite negotiations, coordination, concurrent negotiations, multi-deal, One-to-many negotiations, procurement, asynchronous offers}
}

Conflict resolution is essential to obtain cooperation in many scenarios such as politics and business, as well as our day to day life. The importance of conflict resolution has driven research in many fields like anthropology, social science, psychology, mathematics, biology and, more recently, in artificial intelligence. Computer science and artificial intelligence have, in turn, been inspired by theories and techniques from these disciplines, which has led to a variety of computational models and approaches, such as automated negotiation, group decision making, argumentation, preference aggregation, and human-machine interaction. To bring together the different research strands and disciplines in conflict resolution, the Workshop on Conflict Resolution in Decision Making (COREDEMA) was organized. This special issue benefited from the workshop series, and consists of significantly extended and revised selected papers from the ECAI 2016 COREDEMA workshop, as well as completely new contributions.

@article{ArtificialIntelligenceTechniquesforConflictResolution,
  author = {Reyhan Aydo{\u{g}}an and Tim Baarslag and Enrico Gerding},
  title = {Artificial Intelligence Techniques for Conflict Resolution},
  journal = {Group Decision and Negotiation},
  month = {May},
  year = {2021},
  issn = {1572-9907},
  url = {https://doi.org/10.1007/s10726-021-09738-x},  
  doi = {10.1007/s10726-021-09738-x},
  keywords = {Conflict resolution, Agent-based negotiation, Automated negotiation, Argumentation, Game theory}
}

Our research is developing flexible strategies for forming and routing future platoons of automated urban logistics vehicles. We propose the notion of compensational platooning using automated negotiation between agents representing vehicles. After the vehicles reach the end of a common route, an agent can propose part of its route along with a monetary value to platoon partners for further together-travel. If negotiation is successful, a new platoon is formed and follows the proposed route. If the compensation is too small or the route proposed oversteps the agent's limitations, the offer is rejected and the vehicles continue their travel separately. A contribution of this paper is a negotiation strategy that proposes compensation based on beliefs of what the opponent's payment threshold would be. In doing so, the bid with the highest acceptance likelihood is calculated, keeping negotiations short and effective. Our model is tested on a synthetic network and a real urban example. We show that by using negotiation, vehicles can identify mutually beneficial new routes that a centralised/distributed approach would not find, with utility improvements of up to 8{\%}.

@inproceedings{Seb21,
  author = {Sebe, S{\^i}nziana-Maria and Baarslag, Tim and M{\"u}ller, J{\"o}rg P.},
  title = {Automated Negotiation Mechanism and Strategy for Compensational Vehicular Platooning},
  booktitle = {PRIMA 2020: Principles and Practice of Multi-Agent Systems},
  publisher = {Springer International Publishing},
  year = {2021},
  pages = {317--324},
  address = {Cham},
  editor = {Uchiya, Takahiro and Bai, Quan and Marsá Maestre, Iván},
  url = {https://doi.org/10.1007/978-3-030-69322-0_20},  
  doi = {10.1007/978-3-030-69322-0_20}
}

The Automated Negotiating Agents Competition (ANAC) is a yearly-organized international contest in which participants from all over the world develop intelligent negotiating agents for a variety of negotiation problems. To facilitate the research on agent-based negotiation, the organizers introduce new research challenges every year. ANAC 2019 posed five negotiation challenges: automated negotiation with partial preferences, repeated human-agent negotiation, negotiation in supply-chain management, negotiating in the strategic game of Diplomacy, and in the Werewolf game. This paper introduces the challenges and discusses the main findings and lessons learnt per league.

@inproceedings{ANAC2019,
  author = {Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Fujita, Katsuhide and Mell, Johnathan and Gratch, Jonathan and de Jonge, Dave and Mohammad, Yasser and Nakadai, Shinji and Morinaga, Satoshi and Osawa, Hirotaka and Aranha, Claus and Jonker, Catholijn M.},
  title = {Challenges and Main Results of the Automated Negotiating Agents Competition (ANAC) 2019},
  booktitle = {Multi-Agent Systems and Agreement Technologies},
  publisher = {Springer International Publishing},
  year = {2020},
  pages = {366--381},
  address = {Cham},
  editor = {Bassiliades, Nick and Chalkiadakis, Georgios and de Jonge, Dave},
  url = {https://link.springer.com/chapter/10.1007/978-3-030-66412-1_23},  
  doi = {10.1007/978-3-030-66412-1_23}
}

This paper presents an automated peer-to-peer negotiation strategy for settling energy contracts among prosumers in a Residential Energy Cooperative considering heterogeneity prosumer preferences. The heterogeneity arises from prosumers' evaluation of energy contracts through multiple societal and environmental criteria and the prosumers' private preferences over those criteria. The prosumers engage in bilateral negotiations with peers to mutually agree on periodical energy contracts/loans consisting of the energy volume to be exchanged at that period and the return time of the exchanged energy. The negotiating prosumers navigate through a common negotiation domain consisting of potential energy contracts and evaluate those contracts from their valuations on the entailed criteria against a utility function that is robust against generation and demand uncertainty. From the repeated interactions, a prosumer gradually learns about the compatibility of its peers in reaching energy contracts that are closer to Nash solutions. Empirical evaluation on real demand, generation and storage profiles -- in multiple system scales -- illustrates that the proposed negotiation based strategy can increase the system efficiency (measured by utilitarian social welfare) and fairness (measured by Nash social welfare) over a baseline strategy and an individual flexibility control strategy representing the status quo strategy. We thus elicit system benefits from peer-to-peer flexibility exchange already without any central coordination and market operator, providing a simple yet flexible and effective paradigm that complements existing markets.

@article{Cha20,
  author = {Shantanu Chakraborty and Tim Baarslag and Michael Kaisers},
  title = {Automated peer-to-peer negotiation for energy contract settlements in residential cooperatives},
  journal = {Applied Energy},
  year = {2020},
  volume = {259},
  pages = {114173},
  issn = {0306-2619},
  url = {http://www.sciencedirect.com/science/article/pii/S0306261919318604},  
  doi = {https://doi.org/10.1016/j.apenergy.2019.114173},
  keywords = {Automated negotiation, Energy contract, Multiagent system, P2P energy exchange, Market design}
}

We present the results of the 2nd Annual Human-Agent League of the Automated Negotiating Agent Competition. Building on the success of the previous year's results, a new challenge was issued that focused exploring the likeability-success tradeoff in negotiations. By examining a series of repeated negotiations, actions may affect the relationship between automated negotiating agents and their human competitors over time. The results presented herein support a more complex view of human-agent negotiation and capture of integrative potential (win-win solutions). We show that, although likeability is generally seen as a tradeoff to winning, agents are able to remain well-liked while winning if integrative potential is not discovered in a given negotiation. The results indicate that the top-performing agent in this competition took advantage of this loophole by engaging in favor exchange across negotiations (cross-game logrolling). These exploratory results provide information about the effects of different submitted `black-box' agents in human-agent negotiation and provide a state-of-the-art benchmark for human-agent design.

@inproceedings{IAGO2018,
  author = {Johnathan Mell and Jonathan Gratch and Reyhan Aydo{\u{g}}an and Tim Baarslag and Catholijn M. Jonker},
  title = {The Likeability-Success Tradeoff: Results of the 2nd Annual Human-Agent Automated Negotiating Agents Competition},
  booktitle = {2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)},
  month = {Sep},
  year = {2019},
  pages = {1-7},
  issn = {2156-8103},
  url = {https://ieeexplore.ieee.org/document/8925437},  
  doi = {10.1109/ACII.2019.8925437},
  keywords = {Task analysis;Bars;Games;Buildings;Robustness;Measurement;Graphical user interfaces;human agent interaction;negotiation;empirical results in HCI}
}

@inproceedings{Tan19AAAI,
  author = {Tang, Hongyao and Hao, Jianye and Wang, Li and Baarslag, Tim and Wang, Zan},
  title = {An Optimal Rewiring Strategy for Cooperative Multiagent Social Learning},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2019},
  volume = {33},
  pages = {10049--10050},
  url = {https://ojs.aaai.org//index.php/AAAI/article/view/5161},  
  doi = {10.1609/aaai.v33i01.330110049}
}

Designing agents that can efficiently learn and integrate user's preferences into decision making pro-cesses is a key challenge in automated negotiation. While accurate knowledge of user preferences is highly desirable, eliciting the necessary information might be rather costly, since frequent user interactions may cause inconvenience. Therefore, efficient elicitation strategies (minimizing elicitation costs) for inferring relevant information are critical. We introduce a stochastic, inverse-ranking utility model compatible with the Gaussian Process preference learning framework and integrate into a (belief) Markov Decision Process paradigm which formalizes automated negotiation processes with incomplete information. Our utility model, which naturally maps ordinal preferences (inferred from the user) into (random) utility values (with the randomness reflecting the underlying uncertainty), provides the basic quantitative modeling ingredient for automated (agent-based) negotiation.

@article{GaussianProcessUtilityModels,
  author = {Leahu, Haralambie and Kaisers, Michael and Baarslag, Tim},
  title = {Automated Negotiation with Gaussian Process-based Utility Models},
  booktitle = {Proceedings of the 28th International Joint Conference on Artificial Intelligence},
  publisher = {AAAI Press},
  year = {2019},
  pages = {421–427},  
  series = {IJCAI'19},
  address = {Macau, China},
  url = {https://dl.acm.org/doi/abs/10.5555/3367032.3367093},  
  doi = {10.5555/3367032.3367093}
}

In this paper, we propose a general two-objective Markov Decision Process (MDP) modeling paradigm for automated negotiation with incomplete information, in which preference elicitation alternates with negotiation actions, with the objective to optimize negotiation outcomes. The key ingredient in our MDP framework is a stochastic utility model governed by a Gaussian law, formalizing the agent's belief (uncertainty) over the user's preferences. Our belief model is fairly general and can be updated in real time as new data becomes available, which makes it a fundamental modeling too.

@inproceedings{PreferenceLearningUsingGaussianUncertaintyModels,
  author = {Leahu, Haralambie and Kaisers, Michael and Baarslag, Tim},
  title = {Preference Learning in Automated Negotiation Using Gaussian Uncertainty Models},
  booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2019},
  pages = {2087--2089},  
  series = {AAMAS '19},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=3306127.3332019},
  keywords = {automated negotiation, gaussian processes, preference elicitation}
}

With the increasing potential for the use of autonomous negotiating agents in real world applications, there is also an increasing interest to create negotiating agents that are generally applicable in different negotiation settings. The variety of settings and opponents that may be encountered prohibits the use of a single predefined negotiation strategy, and hence the agent should be able to learn such a strategy autonomously. To this end we propose RLBOA, a modular framework that facilitates the creation of autonomous negotiation agents using reinforcement learning. The framework allows for the creation of agents that are capable of negotiating effectively in many different scenarios. A big challenge in using reinforcement learning for autonomous negotiation is the diversity of settings as well as the size of the state and action spaces. To overcome this we leverage the modular BOA-framework, which decouples the negotiation strategy into a Bidding strategy, an Opponent model and an Acceptance condition. Furthermore, we project the multidimensional contract space onto the one dimensional utility axis which enables a compact and generic state and action description. We demonstrate the value of the RLBOA framework by implementing an agent that uses tabular Q-learning on the compressed state and action space to learn a bidding strategy. We show that the resulting agent is able to learn well-performing bidding strategies in a range of negotiation settings and is able to generalize across opponents and domains.

@inproceedings{BaarslagRLBOA,
  author = {Jasper Bakker and Aron Hammond and Daan Bloembergen and Tim Baarslag},
  title = {RLBOA: A Modular Reinforcement Learning Framework for Autonomous Negotiating Agents},
  booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2019},
  pages = {260--268},  
  series = {AAMAS '19},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=3306127.3331701},
  keywords = {Automated negotiation, Negotiation agent, Bargaining and negotiation, Learning agent-to-agent interactions, Reinforcement Learning}
}

Autonomous agents negotiating on our behalf find applications in everyday life in many domains such as high frequency trading, cloud computing and the smart grid among others. The agents negotiate with one another to reach the best agreement for the users they represent. An obstacle in the future of automated negotiators is that the agent may not always have a priori information about the preferences of the user it represents. The purpose of this work is to develop an agent that will be able to negotiate given partial information about the user's preferences. First, we present a new partial information model that is supplied to the agent, which is based on categorical data in the form of pairwise comparisons of outcomes instead of precise utility information. Using this partial information, we develop an estimation model that uses linear optimization and translates the information into utility estimates. We test our methods in a negotiation scenario based on a smart grid cooperative where agents participate in energy trade-offs. The results show that already with very limited information the model becomes accurate quickly and performs well in an actual negotiation setting. Our work provides valuable insight into how uncertainty affects an agent's negotiation performance, how much information is needed to be able to formulate an accurate user model, and shows a capability of negotiating effectively with minimal user feedback.

@inproceedings{Tsi18,
  author = {Tsimpoukis, Dimitrios and Baarslag, Tim and Kaisers, Michael and Paterakis, Nikolaos},
  title = {Automated Negotiations Under User Preference Uncertainty: A Linear Programming Approach},
  booktitle = {Agreement Technologies},
  publisher = {Springer International Publishing},
  month = {Jan},
  year = {2019},
  pages = {115--129},
  address = {Cham},
  url = {https://www.springerprofessional.de/en/automated-negotiations-under-user-preference-uncertainty-a-linea/16601794},  
  doi = {10.1007/978-3-030-17294-7_9}
}

Multiagent coordination is a key problem in cooperative multiagent systems (MASs). It has been widely studied in both fixed-agent repeated interaction setting and static social learning framework. However, two aspects of dynamics in real-world MASs are currently neglected. First, the network topologies can change during the course of interaction dynamically. Second, the interaction utilities can be different among each pair of agents and usually unknown before interaction. Both issues mentioned above increase the difficulty of coordination. In this paper, we consider the multiagent social learning in a dynamic environment in which agents can alter their connections and interact with randomly chosen neighbors with unknown utilities beforehand. We propose an optimal rewiring strategy to select most beneficial peers to maximize the accumulated payoffs in long-run interactions. We empirically demonstrate the effects of our approach in a variety of large-scale MASs.

@inproceedings{Tan19,
  author = {Tang, Hongyao and Hao, Jianye and Wang, Li and Wang, Zan and Baarslag, Tim},
  title = {An Optimal Rewiring Strategy for Cooperative Multiagent Social Learning},
  booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2019},
  pages = {2209--2211},  
  series = {AAMAS '19},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=3306127.3332060},
  keywords = {learning agent-to-agent interactions (negotiation, trust, coordination), multiagent learning, social simulation}
}

The game of Diplomacy has been used as a test case for complex automated negotiations for a long time, but to date very few successful negotiation algorithms have been implemented for this game. We have therefore decided to include a Diplomacy tournament within the annual Automated Negotiating Agents Competition (ANAC). In this paper we present the setup and the results of the ANAC 2017 Diplomacy Competition and the ANAC 2018 Diplomacy Challenge. We observe that none of the negotiation algorithms submitted to these two editions have been able to significantly improve the performance over a non-negotiating baseline agent. We analyze these algorithms and discuss why it is so hard to write successful negotiation algorithms for Diplomacy. Finally, we provide experimental evidence that, despite these results, coalition formation and coordination do form essential elements of the game.

@inproceedings{Diplomacy20172018,
  author = {Dave de Jonge and Tim Baarslag and Reyhan Aydo{\u{g}}an and Catholijn Jonker and Katsuhide Fujita and Takayuki Ito},
  title = {The Challenge of Negotiation in the Game of Diplomacy},
  booktitle = {Agreement Technologies},
  publisher = {Springer International Publishing},
  year = {2019},
  pages = {100--114},
  address = {Cham},
  url = {https://link.springer.com/chapter/10.1007/978-3-030-17294-7_8},  
  doi = {10.1007/978-3-030-17294-7_8}
}

The Automated Negotiating Agents Competition (ANAC) is annually organized competition to facilitate the research on automated negotiation. This paper presents the ANAC 2017 Repeated Multilateral Negotiation League. As human negotiators do, agents are supposed to learn from their previous negotiations and improve their negotiation skills over time. Especially, when they negotiate with the same opponent on the same domain, they can adopt their negotiation strategy according to their past experiences. They can adjust their acceptance threshold or bidding strategy accordingly. In ANAC 2017, participants aimed to develop such a negotiating agent. Accordingly, this paper describes the competition settings and results with a brief description of the winner negotiation strategies.

@inproceedings{ANAC2017,
  author = {Aydo{\u{g}}an, Reyhan and Fujita, Katsuhide and Baarslag, Tim and Jonker, Catholijn M. and Ito, Takayuki},
  title = {ANAC 2017: Repeated Multilateral Negotiation League},
  booktitle = {Advances in Automated Negotiations},
  publisher = {Springer Singapore},
  year = {2021},
  pages = {101--115},
  address = {Singapore},
  editor = {Ito, Takayuki and Zhang, Minjie and Aydoğan, Reyhan}
}

This is an extension from a selected paper from JSAI2019. There are a number of research challenges in the field of Automated Negotiation. The Ninth International Automated Negotiating Agent Competition encourages participants to develop effective negotiating agents, which can negotiate with multiple opponents more than once. This paper discusses research challenges for such negotiations as well as presenting the competition set-up and results. The results show that winner agents mostly adopt hybrid bidding strategies that take their opponents' preferences as well as their strategy into account.

@inproceedings{ANAC2018,
  author = {Aydo{\u{g}}an, Reyhan and Fujita, Katsuhide and Baarslag, Tim and Jonker, Catholijn M. and Ito, Takayuki},
  title = {ANAC 2018: Repeated Multilateral Negotiation League},
  booktitle = {Advances in Artificial Intelligence},
  publisher = {Springer International Publishing},
  year = {2020},
  pages = {77--89},
  address = {Cham},
  editor = {Ohsawa, Yukio and Yada, Katsutoshi and Ito, Takayuki and Takama, Yasufumi and Sato-Shimokawara, Eri and Abe, Akinori and Mori, Junichiro and Matsumura, Naohiro},
  url = {https://www.jstage.jst.go.jp/article/pjsai/JSAI2019/0/JSAI2019_2F1E301/_article/-char/ja}
}

In recommender systems, human preferences are identified by a number of individual components with complicated interactions and properties. Recently, the dynamicity of preferences has been the focus of several studies. The changes in user preferences can originate from substantial reasons, like personality shift, or transient and circumstantial ones, like seasonal changes in item popularities. Disregarding these temporal drifts in modelling user preferences can result in unhelpful recommendations. Moreover, different temporal patterns can be associated with various preference domains, and preference components and their combinations. These components comprise preferences over features, preferences over feature values, conditional dependencies between features, socially-influenced preferences, and bias. For example, in the movies domain, the user can change his rating behaviour (bias shift), her preference for genre over language (feature preference shift), or start favouring drama over comedy (feature value preference shift). In this paper, we first propose a novel latent factor model to capture the domain-dependent component-specific temporal patterns in preferences. The component-based approach followed in modelling the aspects of preferences and their temporal effects enables us to arbitrarily switch components on and off. We evaluate the proposed method on three popular recommendation datasets and show that it significantly outperforms the most accurate state-of-the-art static models. The experiments also demonstrate the greater robustness and stability of the proposed dynamic model in comparison with the most successful models to date. We also analyse the temporal behaviour of different preference components and their combinations and show that the dynamic behaviour of preference components is highly dependent on the preference dataset and domain. Therefore, the results also highlight the importance of modelling temporal effects but also underline the advantages of a component-based architecture that is better suited to capture domain-specific balances in the contributions of the aspects.

@article{Zaf19,
  author = {Farhad Zafari and Irene Moser and Tim Baarslag},
  title = {Modelling and analysis of temporal preference drifts using a component-based factorised latent approach},
  journal = {Expert Systems with Applications},
  year = {2019},
  volume = {116},
  pages = {186 - 208},
  issn = {0957-4174},
  url = {http://www.sciencedirect.com/science/article/pii/S0957417418305815},  
  doi = {https://doi.org/10.1016/j.eswa.2018.09.010},
  keywords = {Latent factor models, Bias, Feature preferences, Feature value preferences, Temporal dynamics, Preference drift}
}

We present the results of the first annual Human-Agent League of ANAC. By introducing a new human-agent negotiating platform to the research community at large, we facilitated new advancements in human-aware agents. This has succeeded in pushing the envelope in agent design, and creating a corpus of useful human-agent interaction data. Our results indicate a variety of agents were submitted, and that their varying strategies had distinct outcomes on many measures of the negotiation. These agents approach the problems endemic to human negotiation, including user modeling, bidding strategy, rapport techniques, and strategic bargaining. Some agents employed advanced tactics in information gathering or emotional displays and gained more points than their opponents, while others were considered more `likeable' by their partners.

@inproceedings{IAGO2017,
  author = {Mell, Johnathan and Gratch, Jonathan and Baarslag, Tim and Aydo\u{g}an, Reyhan and Jonker, Catholijn M.},
  title = {Results of the First Annual Human-Agent League of the Automated Negotiating Agents Competition},
  booktitle = {Proceedings of the 18th International Conference on Intelligent Virtual Agents},
  publisher = {Association for Computing Machinery},
  year = {2018},
  pages = {23--28},  
  series = {IVA '18},
  address = {New York, NY, USA},
  url = {http://doi.acm.org/10.1145/3267851.3267907},  
  doi = {10.1145/3267851.3267907},
  keywords = {Human-Agent Negotiation, IAGO Negotiation Platform}
}

This paper presents an automated peer-to-peer (P2P) negotiation strategy for settling energy contracts among prosumers in a Residential Energy Cooperative (REC) considering heterogeneous prosumer preferences. The heterogeneity arises from prosumers' evaluation of energy contracts through multiple societal and environmental criteria and the prosumers' private preferences over those criteria. The prosumers engage in bilateral negotiations with peers to mutually agree on periodical energy contracts/loans that consist of an energy volume to be exchanged at that period and the return time of the exchanged energy. The prosumers keep an ordered preference profile of possible energy contracts by evaluating the contracts from their own valuations on the entailed criteria, and iteratively offer the peers contracts until an agreement is formed. A prosumer embeds the valuations into a utility function that further considers uncertainties imposed by demand and generation profiles. Empirical evaluation on real demand, generation and storage profiles illustrates that the proposed negotiation based strategy is able to increase the system efficiency (measured by utilitarian social welfare) and fairness (measured by Nash social welfare) over a baseline strategy and an individual flexibility control strategy. We thus elicit system benefits from P2P flexibility exchange already with few agents and without central coordination, providing a simple yet flexible and effective paradigm that may complement existing markets.

@inproceedings{Cha18,
  author = {Shantanu Chakraborty and Tim Baarslag and Michael Kaisers},
  title = {Energy Contract Settlements through Automated Negotiation in Residential Cooperatives},
  booktitle = {2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)},
  month = {Oct},
  year = {2018},
  pages = {1-6},  
  organization = {IEEE},
  url = {https://arxiv.org/abs/1807.10978},  
  doi = {10.1109/SmartGridComm.2018.8587537},
  keywords = {Contracts;Batteries;Smart grids;Uncertainty;Peer-to-peer computing;Energy exchange;Protocols}
}

Energy efficient festival electrification can be viewed as a middle-consumption problem, standing between smart household applications and larger commercial consumers. The optimal deployment of different resources, such as local renewable energy production (RES), diesel generators (DG) and energy storage systems (ESS) may bring about significant financial gain for the organizer, and is usually framed as an off-grid or limited grid-connection problem. This makes online planning particularly challenging due to the uncertainty related to the RES production, constraints regarding the operation of the diesel generators and limitations of the grid connection. In this paper a new online planning algorithm based on two-stage stochastic programming is proposed in order to address the aforementioned challenges and provide minimal-cost, uninterrupted, and sustainable electrification of festivals under dynamically priced grid energy. Data based on real festival events are used in order to illustrate the effectiveness of the proposed methodology.

@inproceedings{Pap18,
  author = {Iliana Pappi and Tim Baarslag and Michael Kaisers and Nikolaos G. Paterakis},
  title = {An Uncertainty-Aware Online Planning Algorithm for the Sustainable Electrification of Festivals},
  booktitle = {International Conference on Smart Energy Systems and Technologies (SEST 2018)},
  year = {2018},
  pages = {1-6},
  url = {https://homepages.cwi.nl/~baarslag/pub/An_Uncertainty-Aware_Online_Planning_Algorithm_for_the_Sustainable_Electrification_of_Festivals.pdf},  
  doi = {10.1109/SEST.2018.8495825},
  keywords = {energy storage, festival electrification, online planning, renewable energy, stochastic programming}
}

Computers that negotiate on behalf of humans hold great promise for the future and will even become indispensable in emerging application domains such as the smart grid, autonomous driving, and the Internet of Things. An important obstacle is that in many real-life settings, it is impossible to elicit all information necessary to be sensitive to the individual needs and requirements of users. This makes it a lot more challenging for the computer to decide on the right negotiation strategy; however, new methods are being created at CWI that make considerable progress towards solving this problem.

@article{BaarslagERCIM,
  author = {Tim Baarslag},
  title = {Computers that negotiate on our behalf},
  journal = {ERCIM News},
  month = {January},
  year = {2018},
  number = {112},
  pages = {36--37},
  editors = {Jop Briët and Simon Perdrix}
}

Computers that negotiate on our behalf hold great promise for the future and will even become indispensable in emerging application domains such as the smart grid, autonomous driving, and the Internet of Things. Much research has thus been expended to create agents that are able to negotiate in an abundance of circumstances. However, up until now, truly autonomous negotiators have rarely been deployed in real-world applications. This paper sizes up current negotiating agents and explores a number of technological, societal and ethical challenges that autonomous negotiation systems are bringing about. The questions we address are: in what sense are these systems autonomous, what has been holding back their further proliferation, and is their spread something we should encourage? We relate the automated negotiation research agenda to dimensions of autonomy and distill three major themes that we believe will propel autonomous negotiation forward: accurate representation, long-term perspective, and user trust. We argue these orthogonal research directions need to be aligned and advanced in unison to sustain tangible progress in the field.

@inbook{BaarslagChallengesVisionary,
  author = {Tim Baarslag and Michael Kaisers and Enrico H. Gerding and Catholijn M. Jonker and Jonathan Gratch},
  title = {Computers That Negotiate on Our Behalf: Major Challenges for Self-sufficient, Self-directed, and Interdependent Negotiating Agents},
  booktitle = {Autonomous Agents and Multiagent Systems: AAMAS 2017 Workshops, Visionary Papers, São Paulo, Brazil, May 8-12, 2017, Revised Selected Papers},
  publisher = {Springer International Publishing},
  year = {2017},
  volume = {10643},
  pages = {143--163},  
  series = {Lecture Notes in Computer Science},
  address = {Cham},
  editor = {Gita Sukthankar and Juan A. Rodríguez-Aguilar},
  url = {https://doi.org/10.1007/978-3-319-71679-4_10},  
  doi = {10.1007/978-3-319-71679-4_10}
}

Computers that negotiate on our behalf hold great promise for the future and will even become indispensable in emerging application domains such as the smart grid and the Internet of Things. Much research has thus been expended to create agents that are able to negotiate in an abundance of circumstances. However, up until now, truly autonomous negotiators have rarely been deployed in real-world applications. This paper sizes up current negotiating agents and explores a number of technological, societal and ethical challenges that autonomous negotiation systems have brought about. The questions we address are: in what sense are these systems autonomous, what has been holding back their further proliferation, and is their spread something we should encourage? We relate the automated negotiation research agenda to dimensions of autonomy and distill three major themes that we believe will propel autonomous negotiation forward: accurate representation, long-term perspective, and user trust. We argue these orthogonal research directions need to be aligned and advanced in unison to sustain tangible progress in the field.

@inproceedings{BaarslagChallenges,
  author = {Tim Baarslag and Michael Kaisers and Enrico H. Gerding and Catholijn M. Jonker and Jonathan Gratch},
  title = {When will negotiation agents be able to represent us? The challenges and opportunities for autonomous negotiators},
  booktitle = {Proceedings of the Twenty-sixth International Joint Conference on Artificial Intelligence},
  year = {2017},
  pages = {4684--4690},  
  series = {IJCAI'17},
  address = {Melbourne, Australia},
  url = {https://doi.org/10.24963/ijcai.2017/653},  
  doi = {10.24963/ijcai.2017/653}
}

The Pocket Negotiator (PN) is a negotiation support system developed at TU Delft as a tool for supporting people in bilateral negotiations over multi-issue negotiation problems in arbitrary domains. Users are supported in setting their preferences, estimating those of their opponent, during the bidding phase and sealing the deal. We describe the overall architecture, the essentials of the underlying techniques, the form that support takes during the negotiation phases, and we share evidence of the effectiveness of the Pocket Negotiator.

@inbook{PocketNegotiatorEUMAS,
  author = {Jonker, Catholijn M. and Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Broekens, Joost and Detweiler, Christian A. and Hindriks, Koen V. and Huldtgren, Alina and Pasman, Wouter},
  title = {An Introduction to the Pocket Negotiator: A General Purpose Negotiation Support System},
  booktitle = {Multi-Agent Systems and Agreement Technologies: 14th European Conference, EUMAS 2016, and 4th International Conference, AT 2016, Valencia, Spain, December 15-16, 2016, Revised Selected Papers},
  publisher = {Springer International Publishing},
  year = {2017},
  volume = {10207},
  pages = {13--27},
  address = {Cham},
  editor = {Criado Pacheco, Natalia and Carrascosa, Carlos and Osman, Nardine and Julián Inglada, Vicente},
  url = {http://dx.doi.org/10.1007/978-3-319-59294-7_2},  
  doi = {10.1007/978-3-319-59294-7_2}
}

In this article, we introduce a new paradigm to achieve Pareto optimality in group decision-making processes: bottom-up approaches to Pareto optimality. It is based on the idea that, while resolving a conflict in a group, individuals may trust some members more than others; thus, they may be willing to cooperate and share more information with those members. Therefore, one can divide the group into subgroups where more cooperative mechanisms can be formed to reach Pareto optimal outcomes. This is the first work that studies such use of a bottom-up approach to achieve Pareto optimality in conflict resolution in groups. First, we prove that an outcome that is Pareto optimal for subgroups is also Pareto optimal for the group as a whole. Then, we empirically analyze the appropriate conditions and achievable performance when applying bottom-up approaches under a wide variety of scenarios based on real-life datasets. The results show that bottom-up approaches are a viable mechanism to achieve Pareto optimality with applications to group decision-making, negotiation teams, and decision making in open environments.

@article{TeamParetoKAIS,
  author = {Sanchez-Anguix, Victor and Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Jonker, Catholijn},
  title = {Bottom-up approaches to achieve Pareto optimal agreements in group decision making},
  journal = {Knowledge and Information Systems},
  month = {Nov},
  year = {2019},
  volume = {61},
  number = {2},
  pages = {1019--1046},
  issn = {0219-3116},
  url = {https://doi.org/10.1007/s10115-018-01325-y},  
  doi = {10.1007/s10115-018-01325-y}
}

Classically, disciplines like negotiation and decision making have focused on reaching Pareto optimal solutions due to its stability and efficiency properties. Despite the fact that many practical and theoretical algorithms have successfully attempted to provide Pareto optimal solutions, they have focused on attempting to reach Pareto Optimality using horizontal approaches, where optimality is calculated taking into account every participant at the same time. Sometimes, this may prove to be a difficult task (e.g., conflict, mistrust, no information sharing, etc.). In this paper, we explore the possibility of achieving Pareto Optimal outcomes in a group by using a bottom-up approach: discovering Pareto optimal outcomes by interacting in subgroups. We analytically show that the set of Pareto optimal outcomes in a group covers the Pareto optimal outcomes within its subgroups. This theoretical finding can be applied in a variety of scenarios such as negotiation teams, multi-party negotiation, and team formation to social recommendation. Additionally, we empirically test the validity and practicality of this proof in a variety of decision making domains and analyze the usability of this proof in practical situations.

@inbook{TeamParetoCOREDEMA2016,
  author = {Sanchez-Anguix, Victor and Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Jonker, Catholijn M.},
  title = {Can We Reach Pareto Optimal Outcomes Using Bottom-Up Approaches?},
  booktitle = {Conflict Resolution in Decision Making: Second International Workshop, COREDEMA 2016, The Hague, The Netherlands, August 29-30, 2016, Revised Selected Papers},
  publisher = {Springer International Publishing},
  month = {Apr},
  year = {2017},
  pages = {19--35},
  address = {Cham},
  editor = {Aydoğan, Reyhan and Baarslag, Tim and Gerding, Enrico and Jonker, Catholijn M. and Julian, Vicente and Sanchez-Anguix, Victor},
  url = {https://link.springer.com/content/pdf/10.1007/978-3-319-57285-7\_2.pdf},  
  doi = {10.1007/978-3-319-57285-7\_2},
  keywords = {Pareto optimality, Agreement technologies, Group decision making, Multi-agent systems, Artificial intelligence}
}

The annual International Automated Negotiating Agents Competition (ANAC) is used by the automated negotiation research community to benchmark and evaluate its work andto challenge itself. The benchmark problems and evaluation results and the protocols and strategies developed are available to the wider research community.

@inproceedings{ANACAAAI,
  author = {Jonker, Catholijn M. and Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Fujita, Katsuhide and Ito, Takayuki and Hindriks, Koen},
  title = {Automated Negotiating Agents Competition (ANAC)},
  booktitle = {Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence and Twenty-Ninth Innovative Applications of Artificial Intelligence Conference},
  month = {Feb},
  year = {2017},
  pages = {5070-5072},
  url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14745/14021},
  keywords = {benchmark, competition, automated negotiation, protocol, profile}
}

Young and early-career researchers at the 2016 Heidelberg Laureate Forum discuss how the frontier between mathematics and computer science is shifting, what the future promises, and the implications the frontier's shape and dynamics will have on both fields.

@article{HeidelbergLaureateForum,
  author = {Begoli, Edmon and Schlegel, Vincent and Atiyah, Michael and Adeyemo, Praise and Baarslag, Tim},
  title = {The Heidelberg Laureate Forum on the Moving Frontier Between Mathematics and Computer Science},
  journal = {XRDS},
  publisher = {ACM},
  month = {April},
  year = {2017},
  volume = {23},
  number = {3},
  pages = {46-49},
  issn = {1528-4972},
  address = {New York, NY, USA},
  url = {http://doi.acm.org/10.1145/3055143},  
  doi = {10.1145/3055143}
}

In May 2015, we organized the Sixth International Automated Negotiating Agents Competition (ANAC 2015) in conjunction with AAMAS 2015. ANAC is an international competition that challenges researchers to develop a successful automated negotiator for scenarios where there is incomplete information about the opponent. One of the goals of this competition is to help steer the research in the area of multi-issue negotiations, and to encourage the design of generic negotiating agents that are able to operate in a variety of scenarios. 24 teams from 9 different institutes competed in ANAC 2015. This chapter describes the participating agents and the setup of the tournament, including the different negotiation scenarios that were used in the competition. We report on the results of the qualifying and final round of the tournament.

@incollection{ANAC2015,
  author = {Fujita, Katsuhide and Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Hindriks, Koen and Ito, Takayuki and Jonker, Catholijn},
  title = {The Sixth Automated Negotiating Agents Competition (ANAC 2015)},
  booktitle = {Modern Approaches to Agent-based Complex Automated Negotiation},
  publisher = {Springer},
  year = {2017},
  volume = {674},
  pages = {139--151},
  issn = {1860-949X},
  url = {http://dx.doi.org/10.1007/978-3-319-51563-2\_9},  
  doi = {10.1007/978-3-319-51563-2\_9}
}

The digital economy is based on data sharing yet citizens have little control about how their personal data is being used. While data management during web and app-based use is already a challenge, as the Internet of Things (IoT) scales up, the number of devices accessing and requiring personal data will go beyond what a person can manually assess in terms of data access requests. Therefore, new approaches are needed for managing privacy preferences at scale and providing active consent around data sharing that can improve fidelity of operation in alignment with user intent. To address this challenge, we introduce a novel agent-based approach to negotiate the permission to exchange private data between users and services. Our agent negotiates based on learned preferences from actual users. To evaluate our agent-based approach, we developed an experimental tool to run on people's own smartphones, where users were asked to share their private, real data (e.g. photos, contacts, etc) under various conditions. The agent autonomously negotiates potential agreements for the user, which they can refine by manually continuing the negotiation. The agent learns from these interactions and updates the user model in subsequent interactions. We find that the agent is able to effectively capture the preferences and negotiate on the user's behalf but, surprisingly, does not reduce user engagement with the system. Understanding how interaction interplays with agent-based automation is a key component to successful deployment of negotiating agents in real-life settings and within the IoT context in particular.

@inproceedings{BaarslagNegotiationAgentForPermissionManagement,
  author = {Baarslag, Tim and Alan, Alper T. and Gomer, Richard and Alam, Mudasser and Perera, Charith and Gerding, Enrico H. and Schraefel, M.C.},
  title = {An Automated Negotiation Agent for Permission Management},
  booktitle = {Proceedings of the 2017 International Conference on Autonomous Agents and Multi-agent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2017},
  pages = {380-390},  
  series = {AAMAS '17},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=3091125.3091184},
  keywords = {Automated negotiation, Negotiation agent, Privacy, Permissions, Mobile apps, Negotiation cost, Partial offers, Preference learning}
}

Consider an agent that can autonomously negotiate and coordinate with others in our stead, to reach outcomes and agreements in our interest. Such automated negotiation agents are already common practice in areas such as high frequency trading, and are now finding applications in domains closer to home, which involve not only mere financial optimizations but balanced tradeoffs between multiple issues, such as cost and convenience. As a simple example, a smart thermostat controlling a heat pump could provide demand response to the electricity grid if the inconvenience is offset by the grid relieve incentives. In such situations, the agent represents a user with individual and a priori unknown preferences, which are costly to elicit due to the user bother this incurs. Therefore, the agent needs to strike a balance between increasing the user model accuracy and the inconvenience caused by interacting with the user. To do so, we require a tractable metric for the value of information in an ensuing negotiation, which until now has not been available. In this paper, we propose a decision model that finds the point of diminishing returns for improving the model of user preferences with costly queries. We present a reasoning framework to derive this metric, and show a myopically optimal and tractable stopping criterion for querying the user before a fixed number of negotiation rounds. Our method provides an extensible basis for interactive negotiation agents to evaluate which questions are worth posing given the marginal utility expected to arise from more accurate beliefs.

@inproceedings{BaarslagValueOfInformation,
  author = {Baarslag, Tim and Kaisers, Michael},
  title = {The Value of Information in Automated Negotiation: A Decision Model for Eliciting User Preferences},
  booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2017},
  pages = {391-400},  
  series = {AAMAS '17},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=3091125.3091185},
  keywords = {automated negotiation, negotiation agent, optimal query, preference elicitation, uncertain preferences, user preferences, value of information}
}

A negotiation between agents is typically an incomplete information game, where the agents initially do not know their opponent's preferences or strategy. This poses a challenge, as efficient and effective negotiation requires the bidding agent to take the other's wishes and future behavior into account when deciding on a proposal. Therefore, in order to reach better and earlier agreements, an agent can apply learning techniques to construct a model of the opponent. There is a mature body of research in negotiation that focuses on modeling the opponent, but there exists no recent survey of commonly used opponent modeling techniques. This work aims to advance and integrate knowledge of the field by providing a comprehensive survey of currently existing opponent models in a bilateral negotiation setting. We discuss all possible ways opponent modeling has been used to benefit agents so far, and we introduce a taxonomy of currently existing opponent models based on their underlying learning techniques. We also present techniques to measure the success of opponent models and provide guidelines for deciding on the appropriate performance measures for every opponent model type in our taxonomy.

@article{BaarslagOMSurvey,
  author = {Tim Baarslag and Mark J.C. Hendrikx and Koen V. Hindriks and Catholijn M. Jonker},
  title = {Learning about the opponent in automated bilateral negotiation: a comprehensive survey of opponent modeling techniques},
  journal = {Autonomous Agents and Multi-Agent Systems},
  publisher = {Springer US},
  year = {2016},
  volume = {30},
  number = {5},
  pages = {849--898},
  issn = {1573-7454},
  language = {English},
  url = {http://dx.doi.org/10.1007/s10458-015-9309-1},  
  doi = {10.1007/s10458-015-9309-1},
  keywords = {Negotiation, Software agents, Opponent model, Learning techniques, Automated negotiation, Opponent modeling, Machine learning, Survey}
}

The Internet of Things is expected to generate large amounts of heterogeneous data from diverse sources including physical sensors, user devices and social media platforms. Over the last few years, significant attention has been focused on personal data, particularly data generated by smart wearable and smart home devices. Making personal data available for access and trade is expected to become a part of the data-driven digital economy. In this position paper, we review the research challenges in building personal Databoxes that hold personal data and enable data access by other parties and potentially thus sharing of data with other parties. These Databoxes are expected to become a core part of future data marketplaces.

@article{Perera2016IoTDatabox,
  author = {Perera, Charith and Wakenshaw, Susan Y. L. and Baarslag, Tim and Haddadi, Hamed and Bandara, Arosha K. and Mortier, Richard and Crabtree, Andy and Ng, Irene C. L. and McAuley, Derek and Crowcroft, Jon},
  title = {Valorising the IoT Databox: creating value for everyone},
  journal = {Transactions on Emerging Telecommunications Technologies},
  publisher = {John Wiley & Sons, Ltd},
  year = {2017},
  volume = {28},
  number = {1},
  pages = {1-17},
  issn = {2161-3915},
  url = {http://dx.doi.org/10.1002/ett.3125},  
  doi = {10.1002/ett.3125}
}

This book reports on an outstanding thesis that has significantly advanced the state-of-the-art in the area of automated negotiation. It gives new practical and theoretical insights into the design and evaluation of automated negotiators. It describes an innovative negotiating agent framework that enables systematic exploration of the space of possible negotiation strategies by recombining different agent components. Using this framework, new and effective ways are formulated for an agent to learn, bid, and accept during a negotiation. The findings have been evaluated in four annual instantiations of the International Automated Negotiating Agents Competition (ANAC), the results of which are also outlined here. The book also describes several methodologies for evaluating and comparing negotiation strategies and components, with a special emphasis on performance and accuracy measures.

@book{BaarslagSpringerTheses,
  author = {Tim Baarslag},
  title = {Exploring the Strategy Space of Negotiating Agents: A Framework for Bidding, Learning and Accepting in Automated Negotiation},
  publisher = {Springer International Publishing},
  year = {2016},  
  series = {Springer Theses: Recognizing Outstanding Ph.D. Research},
  url = {http://dx.doi.org/10.1007/978-3-319-28243-5},  
  doi = {10.1007/978-3-319-28243-5}
}

We address the problem of recommending an appliance usage schedule to the homeowner which balances between maximising total savings and maintaining sufficient user convenience. An important challenge within this problem is how to elicit the the user preferences with low intrusiveness, in order to identify new schedules with high cost savings, that still lies within the user's comfort zone. To tackle this problem we propose iDR, an interactive system for generating personalised appliance usage scheduling recommendations that maximise savings and convenience with minimal intrusiveness. In particular, our system learns when to stop interacting with the user during the preference elicitation process, in order to keep the bother cost (e.g., the amount of time the user spends, or the cognitive cost of interacting) minimal. We demonstrate through extensive empirical evaluation on real-world data that our approach improves savings by up to 35\%, while maintaining a significantly lower bother cost, compared to state-of the-art benchmarks.

@inproceedings{TruongSchedulingApplianceUsage,
  author = {Ngoc Cuong Truong and Tim Baarslag and Gopal Ramchurn and Long Tran-Thanh},
  title = {Interactive scheduling of appliance usage in the home},
  booktitle = {The 25th International Joint Conference on Artificial Intelligence},
  publisher = {AAAI Press},
  month = {June},
  year = {2016},
  url = {http://eprints.soton.ac.uk/396670/}
}

This paper studies a search problem involving a robot that is searching for a certain item in an uncertain environment (e.g., searching minerals on the moon) that allows only limited interaction with humans. The uncertainty of the environment comes from the rewards of undiscovered items and the availability of costly human help. The goal of the robot is to maximize the reward of the items found while minimising the search costs. We show that this search problem is polynomially solvable with a novel integration of the human help, which has not been studied in the literature before. Furthermore, we empirically evaluate our solution with simulations and show that it significantly outperforms several benchmark approaches.

@inproceedings{ChenRobotSearch,
  author = {Shaofei Chen and Tim Baarslag and Dengji Zhao and Jing Chen and Lincheng Shen},
  title = {A polynomial time optimal algorithm for robot-human search under uncertainty},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence},
  publisher = {AAAI Press},
  month = {July},
  year = {2016},
  pages = {819-825},  
  series = {IJCAI'16},
  address = {New York, USA},
  url = {http://dl.acm.org/citation.cfm?id=3060621.3060735}
}

On the Android platform, apps make use of personal data as part of their business model, trading location, contacts, photos and more for app use. Few people are particularly aware of the permission settings or make changes to them. We hypothesize that both the difficulty in checking permission settings for all apps on a device, along with the lack of flexibility in deciding what happens to one's data, makes the perceived cost to protect one's privacy too high. In this paper, we present the preliminary results of a study that explores what happens when permission settings are more discretional at install time. We present the results of a pilot experiment, in which we ask users to negotiate which data they are happy to share, and we show that this results in higher user satisfaction than the typical take-it-or-leave-it setting. Our preliminary findings suggest negotiating consent is a powerful interaction mechanism that engages users and can enable them to strike a balance between privacy and pricing concerns.

@inproceedings{BaarslagNegotiationAsAnInteractionMechanism,
  author = {Baarslag, Tim and Alan, Alper T. and Gomer, Richard C. and Liccardi, Ilaria and Marreiros, Helia and Gerding, Enrico H. and Schraefel, M.C.},
  title = {Negotiation As an Interaction Mechanism for Deciding App Permissions},
  booktitle = {Proceedings of the 2016 CHI Conference: Extended Abstracts on Human Factors in Computing Systems},
  publisher = {ACM},
  year = {2016},
  pages = {2012--2019},  
  series = {CHI EA '16},
  address = {New York, NY, USA},
  url = {http://doi.acm.org/10.1145/2851581.2892340},  
  doi = {10.1145/2851581.2892340},
  keywords = {interaction, mobile, negotiation, permissions, privacy}
}

In the past few years, there is a growing interest in automated negotiation in which software agents facilitate negotiation on behalf of their users and try to reach joint agreements. The potential value of developing such mechanisms becomes enormous when negotiation domain is too complex for humans to find agreements (e.g. e-commerce) and when software components need to reach agreements to work together (e.g. web-service composition). Here, one of the major challenges is to design agents that are able to deal with incomplete information about their opponents in negotiation as well as to effectively negotiate on their users? behalves. To facilitate the research in this field, an automated negotiating agent competition has been organized yearly. This paper introduces the research challenges in Automated Negotiating Agent Competition (ANAC) 2014 and explains the competition set up and results. Furthermore, a detailed analysis of the best performing five agents has been examined.

@inbook{ANAC2014Baseline,
  author = {Reyhan Aydo{\u{g}}an and Tim Baarslag and Catholijn M. Jonker and Katsuhide Fujita and Takayuki Ito and Rafik Hadfi and Kohei Hayakawa},
  title = {A Baseline for Non-Linear Bilateral Negotiations: The full results of the agents competing in ANAC 2014},
  booktitle = {Intelligent Computational Systems: A Multi-Disciplinary Perspective},
  publisher = {Bentham Science Publishers},
  year = {2016},  
  series = {Frontiers in Artificial Intelligence},
  url = {http://eprints.soton.ac.uk/399235/}
}

In May 2014, we organized the Fifth International Automated Negotiating Agents Competition (ANAC 2014) in conjunction with AAMAS 2014. ANAC is an international competition that challenges researchers to develop a successful automated negotiator for scenarios where there is incomplete information about the opponent. One of the goals of this competition is to help steer the research in the area of bilateral multi-issue negotiations, and to encourage the design of generic negotiating agents that are able to operate in a variety of scenarios. 21 teams from 13 different institutes competed in ANAC 2014. This chapter describes the participating agents and the setup of the tournament, including the different negotiation scenarios that were used in the competition. We report on the results of the qualifying and final round of the tournament.

@inbook{ANAC2014,
  author = {Fujita, Katsuhide and Aydo{\u{g}}an, Reyhan and Baarslag, Tim and Ito, Takayuki and Jonker, Catholijn},
  title = {The Fifth Automated Negotiating Agents Competition (ANAC 2014)},
  booktitle = {Recent Advances in Agent-based Complex Automated Negotiation},
  publisher = {Springer International Publishing},
  year = {2016},
  volume = {638},
  pages = {211--224},
  address = {Cham},
  editor = {Fukuta, Naoki and Ito, Takayuki and Zhang, Minjie and Fujita, Katsuhide and Robu, Valentin},
  url = {http://dx.doi.org/10.1007/978-3-319-30307-9\_13},  
  doi = {10.1007/978-3-319-30307-9\_13}
}

Negotiation is a process in which parties interact to settle a mutual concern to improve their status quo. Traditionally, negotiation is a necessary, but time-consuming and expensive activity. Therefore, in the last two decades, there has been a growing interest in the automation of negotiation. One of the key challenges for a successful negotiation is that usually only limited information is available about the opponent. Although sharing private information can result in mutual gains, negotiators often avoid this to prevent exploitation. This problem can be partially overcome by deriving information from the opponent's actions. Exploiting this information to learn aspects of the opponent is called opponent modeling. Creating an accurate opponent model is a key factor in improving the quality of the outcome and can further increase the benefits of automated negotiation. Despite the advantages of opponent modeling and two decades of research, there is no recent study that provides an overview of the field. Therefore, in order to stimulate the development of efficient future opponent models, and to outline a research agenda, we provide an overview of existing opponent models in bilateral negotiation. As our main contributions, we classify opponent models using a comprehensive taxonomy and provide recommendations on how to select the best model depending on the negotiation setting.

@inproceedings{BaarslagOMSurveyAAMAS,
  author = {Tim Baarslag and Mark J.C. Hendrikx and Koen V. Hindriks and Catholijn M. Jonker},
  title = {A Survey of Opponent Modeling Techniques in Automated Negotiation},
  booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents and Multi-agent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2016},
  pages = {575--576},  
  series = {AAMAS '16},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=2936924.2937008},
  keywords = {automated negotiation, learning techniques, machine learning, negotiation, opponent model, opponent modeling, software agents, survey}
}

The last two decades have seen a growing interest in automated agents that are able to negotiate on behalf of human negotiators in a wide variety of negotiation domains. One key aspect of a successful negotiating agent is its ability to make appropriate concessions at the right time, especially when there are costs associated with the duration of the negotiation. However, so far, there is no fundamental approach on how much to concede at every stage of the negotiation in such time-sensitive domains. We introduce an efficient solution based on simultaneous search, which is able to select the optimal sequence of offers that maximizes expected payoff, given the agent's beliefs about the opponent. To this end, we show that our approach is consistent with known theoretical results and we demonstrate both its effectiveness and natural properties by applying it to a number of typical negotiation scenarios. Finally, we show in a number of experiments that our solution outperforms other state of the art strategy benchmarks.

@inproceedings{BaarslagSimultaneousSearch,
  author = {Tim Baarslag and Enrico H. Gerding and Reyhan Aydo{\u{g}}an and M.C. Schraefel},
  title = {Optimal Negotiation Decision Functions in Time-Sensitive Domains},
  booktitle = {2015 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)},
  month = {Dec},
  year = {2015},
  volume = {2},
  pages = {190-197},
  url = {http://dx.doi.org/10.1109/WI-IAT.2015.161},  
  doi = {10.1109/WI-IAT.2015.161},
  keywords = {multi-agent systems;negotiation support systems;automated agents;negotiating agent;optimal negotiation decision functions;simultaneous search;time-sensitive domains;Cost function;Electronic mail;Force;Games;Intelligent agents;Planning;Uncertainty;Automated negotiation;Bidding strategy;Cascade model;Concessions;Cost;Costly negotiation;Decision function;Distributive bargaining;Integrative bargaining;Negotiation;Optimal offers;Simultaneous search;Time-sensitive}
}

The Automated Negotiating Agents Competition is an international event that, since 2010, has contributed to the evaluation and development of new techniques and benchmarks for improving the state of the art in automated multi-issue negotiation. A key objective of the competition has been to analyze and search the design space of negotiating agents for agents that are able to operate effectively across a variety of domains. The competition is a valuable tool for studying important aspects of negotiation including profiles and domains, opponent learning, strategies, and bilateral and multilateral protocols. Two of the challenges that remain are how to develop argumentation-based negotiation agents that, in addition to making offers, can inform and argue to obtain an acceptable agreement for both parties; and how to create agents that can negotiate in a human fashion.

@article{BaarslagANAC2010-2015,
  author = {Tim Baarslag and Reyhan Aydo{\u{g}}an and Koen V. Hindriks and Katsuhide Fuijita and Takayuki Ito and Catholijn M. Jonker},
  title = {The Automated Negotiating Agents Competition, 2010-2015},
  journal = {AI Magazine},
  publisher = {Association for the Advancement of Artificial Intelligence (AAAI)},
  month = {12/2015},
  year = {2015},
  volume = {36},
  number = {4},
  pages = {115-118},  
  type = {Competition report},
  url = {http://www.aaai.org/ojs/index.php/aimagazine/article/view/2609}
}

We propose a design in which the user can negotiate a mobile app's permissions to access their personal data. For example, users who prefer not to view ads could opt to pay an additional fee for this. However, negotiating with each app might be cumbersome and difficult to achieve by users. Hence, to make this process easier, we propose an approach that uses an agent-based framework that employs software agents to represent users in their privacy negotiation with the app in an automated manner.

@inproceedings{BaarslagNegotiatingMobileAppPermissions,
  author = {Tim Baarslag and Ilaria Liccardi and Enrico H. Gerding and Richard Gomer and M.C. Schraefel},
  title = {Negotiating Mobile App Permissions},
  booktitle = {Amsterdam privacy conference},
  year = {2015},
  url = {http://eprints.soton.ac.uk/377378/}
}

The last two decades have seen a growing interest in the development of automated agents that are able to negotiate on the user's behalf. When representing a user in a negotiation, it is essential for the agent to understand the user's preferences, without exposing them to elicitation fatigue. To this end, we propose a new model in which a negotiating agent may incrementally elicit the user's preference during the negotiation. We introduce an optimal elicitation strategy that decides, at every stage of the negotiation, how much additional user information to extract at a certain cost. Finally, we demonstrate the effectiveness of our approach by combining our policy with well-known negotiation strategies and show that it significantly outperforms other elicitation strategies.

@inproceedings{BaarslagPandora,
  author = {Tim Baarslag and Enrico H. Gerding},
  title = {Optimal Incremental Preference Elicitation during Negotiation},
  booktitle = {Proceedings of the Twenty-fourth International Joint Conference on Artificial Intelligence},
  year = {2015},
  pages = {3--9},  
  series = {IJCAI'15},
  address = {Buenos Aires, Argentina},  
  organization = {AAAI Press},
  url = {http://dl.acm.org/citation.cfm?id=2832249.2832250}
}

Negotiation is an important activity in human society, and is studied by various disciplines, ranging from economics and game theory, to electronic commerce, social psychology, and artificial intelligence. Traditionally, negotiation is a necessary, but also time-consuming and expensive activity. Therefore, in the last decades there has been a large interest in the automation of negotiation, for example in the setting of e-commerce. This interest is fueled by the promise of automated agents eventually being able to negotiate on behalf of human negotiators. Every year, automated negotiation agents are improving in various ways, and there is now a large body of negotiation strategies available, all with their unique strengths and weaknesses. For example, some agents are able to predict the opponent's preferences very well, while others focus more on having a sophisticated bidding strategy. The problem however, is that there is little incremental improvement in agent design, as the agents are tested in varying negotiation settings, using a diverse set of performance measures. This makes it very difficult to meaningfully compare the agents, let alone their underlying techniques. As a result, we lack a reliable way to pinpoint the most effective components in a negotiating agent. There are two major advantages of distinguishing between the different components of a negotiating agent's strategy: first, it allows the study of the behavior and performance of the components in isolation. For example, it becomes possible to compare the preference learning component of all agents, and to identify the best among them. Second, we can proceed to mix and match different components to create new negotiation strategies., e.g.: replacing the preference learning technique of an agent and then examining whether this makes a difference. Such a procedure enables us to combine the individual components to systematically explore the space of possible negotiation strategies. To develop a compositional approach to evaluate and combine the components, we identify structure in most agent designs by introducing the BOA architecture, in which we can develop and integrate the different components of a negotiating agent. We identify three main components of a general negotiation strategy; namely a bidding strategy (B), possibly an opponent model (O), and an acceptance strategy (A). The bidding strategy considers what concessions it deems appropriate given its own preferences, and takes the opponent into account by using an opponent model. The acceptance strategy decides whether offers proposed by the opponent should be accepted. The BOA architecture is integrated into a generic negotiation environment called Genius, which is a software environment for designing and evaluating negotiation strategies. To explore the negotiation strategy space of the negotiation research community, we amend the Genius repository with various existing agents and scenarios from literature. Additionally, we organize a yearly international negotiation competition (ANAC) to harvest even more strategies and scenarios. ANAC also acts as an evaluation tool for negotiation strategies, and encourages the design of negotiation strategies and scenarios. We re-implement agents from literature and ANAC and decouple them to fit into the BOA architecture without introducing any changes in their behavior. For each of the three components, we manage to find and analyze the best ones for specific cases, as described below. We show that the BOA framework leads to significant improvements in agent design by wining ANAC 2013, which had 19 participating teams from 8 international institutions, with an agent that is designed using the BOA framework and is informed by a preliminary analysis of the different components. In every negotiation, one of the negotiating parties must accept an offer to reach an agreement. Therefore, it is important that a negotiator employs a proficient mechanism to decide under which conditions to accept. When contemplating whether to accept an offer, the agent is faced with the acceptance dilemma: accepting the offer may be suboptimal, as better offers may still be presented before time runs out. On the other hand, accepting too late may prevent an agreement from being reached, resulting in a break off with no gain for either party. We classify and compare state-of-the-art generic acceptance conditions. We propose new acceptance strategies and we demonstrate that they outperform the other conditions. We also provide insight into why some conditions work better than others and investigate correlations between the properties of the negotiation scenario and the efficacy of acceptance conditions. Later, we adopt a more principled approach by applying optimal stopping theory to calculate the optimal decision on the acceptance of an offer. We approach the decision of whether to accept as a sequential decision problem, by modeling the bids received as a stochastic process. We determine the optimal acceptance policies for particular opponent classes and we present an approach to estimate the expected range of offers when the type of opponent is unknown. We show that the proposed approach is able to find the optimal time to accept, and improves upon all existing acceptance strategies. Another principal component of a negotiating agent's strategy is its ability to take the opponent's preferences into account. The quality of an opponent model can be measured in two different ways. One is to use the agent's performance as a benchmark for the model's quality. We evaluate and compare the performance of a selection of state-of-the-art opponent modeling techniques in negotiation. We provide an overview of the factors influencing the quality of a model and we analyze how the performance of opponent models depends on the negotiation setting. We identify a class of simple and surprisingly effective opponent modeling techniques that did not receive much previous attention in literature. The other way to measure the quality of an opponent model is to directly evaluate its accuracy by using similarity measures. We review all methods to measure the accuracy of an opponent model and we then analyze how changes in accuracy translate into performance differences. Moreover, we pinpoint the best predictors for good performance. This leads to new insights concerning how to construct an opponent model, and what we need to measure when optimizing performance. Finally, we take two different approaches to gain more insight into effective bidding strategies. We present a new classification method for negotiation strategies, based on their pattern of concession making against different kinds of opponents. We apply this technique to classify some well-known negotiating strategies, and we formulate guidelines on how agents should bid in order to be successful, which gives insight into the bidding strategy space of negotiating agents. Furthermore, we apply optimal stopping theory again, this time to find the concessions that maximize utility for the bidder against particular opponents. We show there is an interesting connection between optimal bidding and optimal acceptance strategies, in the sense that they are mirrored versions of each other. Lastly, after analyzing all components separately, we put the pieces back together again. We take all BOA components accumulated so far, including the best ones, and combine them all together to explore the space of negotiation strategies. We compute the contribution of each component to the overall negotiation result, and we study the interaction between components. We find that combining the best agent components indeed makes the strongest agents. This shows that the component-based view of the BOA architecture not only provides a useful basis for developing negotiating agents but also provides a useful analytical tool. By varying the BOA components we are able to demonstrate the contribution of each component to the negotiation result, and thus analyze the significance of each. The bidding strategy is by far the most important to consider, followed by the acceptance conditions and finally followed by the opponent model. Our results validate the analytical approach of the BOA framework to first optimize the individual components, and then to recombine them into a negotiating agent.

@phdthesis{BaarslagThesis,
  author = {Tim Baarslag},
  title = {What to Bid and When to Stop},
  month = {Sep},
  year = {2014},
  institution = {Delft University of Technology},
  school = {Delft University of Technology},  
  type = {Dissertation},
  url = {http://dx.doi.org/10.4233/uuid:3df6e234-a7c1-4dbe-9eb9-baadabc04bca},  
  doi = {10.4233/uuid:3df6e234-a7c1-4dbe-9eb9-baadabc04bca}
}

The design of automated negotiators has been the focus of abundant research in recent years. However, due to difficulties involved in creating generalized agents that can negotiate in several domains and against human counterparts, many automated negotiators are domain specific and their behavior cannot be generalized for other domains. Some of these difficulties arise from the differences inherent within the domains, the need to understand and learn negotiators' diverse preferences concerning issues of the domain, and the different strategies negotiators can undertake. In this paper we present a system that enables alleviation of the difficulties in the design process of general automated negotiators termed Genius, a General Environment for Negotiation with Intelligent multi-purpose Usage Simulation. With the constant introduction of new domains, e-commerce and other applications, which require automated negotiations, generic automated negotiators encompass many benefits and advantages over agents that are designed for a specific domain. Based on experiments conducted with automated agents designed by human subjects using Genius we provide both quantitative and qualitative results to illustrate its efficacy. Finally, we also analyze a recent automated bilateral negotiators competition that was based on Genius. Our results show the advantages and underlying benefits of using Genius and how it can facilitate the design of general automated negotiators.

@article{Baarslag12Genius,
  author = {Raz Lin and Sarit Kraus and Tim Baarslag and Dmytro Tykhonov and Koen V. Hindriks and Catholijn M. Jonker},
  title = {Genius: An Integrated Environment for Supporting the Design of Generic Automated Negotiators},
  journal = {Computational Intelligence},
  publisher = {Blackwell Publishing Inc},
  year = {2014},
  volume = {30},
  number = {1},
  pages = {48--70},
  issn = {1467-8640},
  url = {http://dx.doi.org/10.1111/j.1467-8640.2012.00463.x},  
  doi = {10.1111/j.1467-8640.2012.00463.x},
  keywords = {agents competition, automated negotiation, human/computer interaction, bilateral negotiation}
}

In every negotiation with a deadline, one of the negotiating parties must accept an offer to avoid a break off. As a break off is usually an undesirable outcome for both parties, it is important that a negotiator employs a proficient mechanism to decide under which conditions to accept. When designing such conditions, one is faced with the acceptance dilemma: accepting the current offer may be suboptimal, as better offers may still be presented before time runs out. On the other hand, accepting too late may prevent an agreement from being reached, resulting in a break off with no gain for either party. Motivated by the challenges of bilateral negotiations between automated agents and by the results and insights of the automated negotiating agents competition (ANAC), we classify and compare state-of-the-art generic acceptance conditions. We perform extensive experiments to compare the performance of various acceptance conditions in combination with a broad range of bidding strategies and negotiation scenarios. Furthermore we propose new acceptance conditions and we demonstrate that they outperform the other conditions. We also provide insight into why some conditions work better than others and investigate correlations between the properties of the negotiation scenario and the efficacy of acceptance conditions.

@article{Baarslag13DSS,
  author = {Tim Baarslag and Koen V. Hindriks and Catholijn M. Jonker},
  title = {Effective Acceptance Conditions in Real-time Automated Negotiation},
  journal = {Decision Support Systems},
  publisher = {Elsevier Science Publishers B.V.},
  month = {Apr},
  year = {2014},
  volume = {60},
  pages = {68--77},
  issn = {0167-9236},
  address = {Amsterdam, The Netherlands, The Netherlands},
  url = {http://dx.doi.org/10.1016/j.dss.2013.05.021},  
  doi = {10.1016/j.dss.2013.05.021},
  keywords = {Acceptance conditions, Acceptance criteria, Automated negotiation, Real-time bilateral negotiation, When to accept}
}

Motivated by the challenges of bilateral negotiations between people and automated agents we organized the first automated negotiating agents competition (ANAC 2010). The purpose of the competition is to facilitate the research in the area bilateral multi-issue closed negotiation. The competition was based on the Genius environment, which is a General Environment for Negotiation with Intelligent multi-purpose Usage Simulation. The first competition was held in conjunction with the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-10) and was comprised of seven teams. This paper presents an overview of the competition, as well as general and contrasting approaches towards negotiation strategies that were adopted by the participants of the competition. Based on analysis in post--tournament experiments, the paper also attempts to provide some insights with regard to effective approaches towards the design of negotiation strategies.

@inproceedings{Baarslag10ANAC,
  author = {Baarslag, Tim and Hindriks, Koen V. and Jonker, Catholijn M. and Kraus, Sarit and Lin, Raz},
  title = {The First Automated Negotiating Agents Competition (ANAC 2010)},
  booktitle = {New Trends in Agent-based Complex Automated Negotiations},
  publisher = {Springer-Verlag},
  year = {2012},
  volume = {383},
  pages = {113-135},  
  series = {Studies in Computational Intelligence},
  address = {Berlin, Heidelberg},
  editor = {Takayuki Ito and Minjie Zhang and Valentin Robu and Shaheen Fatima and Tokuro Matsuo},
  url = {http://dx.doi.org/10.1007/978-3-642-24696-8_7},  
  doi = {10.1007/978-3-642-24696-8\_7}
}

When a negotiating agent is presented with an offer by its opponent, it is faced with a decision: it can accept the offer that is currently on the table, or it can reject it and continue the negotiation. Both options involve an inherent risk: continuing the negotiation carries the risk of forgoing a possibly optimal offer, whereas accepting runs the risk of missing out on an even better future offer. We approach the decision of whether to accept as a sequential decision problem, by modeling the bids received as a stochastic process. We argue that this is a natural choice in the context of a negotiation with incomplete information, where the future behavior of the opponent is uncertain. We determine the optimal acceptance policies for particular opponent classes and we present an approach to estimate the expected range of offers when the type of opponent is unknown. We apply our method against a wide range of opponents, and compare its performance with acceptance mechanisms of state-of-the-art negotiation strategies. The experiments show that the proposed approach is able to find the optimal time to accept, and improves upon widely used existing acceptance mechanisms.

@inproceedings{Baarslag13AAMAS,
  author = {Baarslag, Tim and Hindriks, Koen V.},
  title = {Accepting Optimally in Automated Negotiation with Incomplete Information},
  booktitle = {Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2013},
  pages = {715--722},  
  series = {AAMAS '13},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=2484920.2485033},
  keywords = {acceptance strategy, negotiation, optimal stopping}
}

When two parties conduct a negotiation, they must be willing to make concessions to achieve a mutually acceptable deal, or face the consequences of no agreement. Therefore, negotiators normally make larger concessions as the deadline is closing in. Many time-based concession strategies have already been proposed, but they are typically heuristic in nature, and therefore, it is still unclear what is the right way to concede toward the opponent. Our aim is to construct optimal concession strategies against specific classes of acceptance strategies. We apply sequential decision techniques to find analytical solutions that optimize the expected utility of the bidder, given certain strategy sets of the opponent. Our solutions turn out to significantly outperform current state of the art approaches in terms of obtained utility. Our results open the way for a new and general concession strategy that can be combined with various existing learning and accepting techniques to yield a fully-fledged negotiation strategy for the alternating offers setting.

@inproceedings{BaarslagOptimalBiddingACAN,
  author = {Tim Baarslag and Rafik Hadfi and Koen V. Hindriks and Takayuki Ito and Catholijn M. Jonker},
  title = {Optimal Non-adaptive Concession Strategies with Incomplete Information},
  booktitle = {Recent Advances in Agent-based Complex Automated Negotiation},
  publisher = {Springer International Publishing},
  year = {2016},
  volume = {638},
  pages = {39--54},
  address = {Cham},
  editor = {Fukuta, Naoki and Ito, Takayuki and Zhang, Minjie and Fujita, Katsuhide and Robu, Valentin},
  url = {http://dx.doi.org/10.1007/978-3-319-30307-9_3},  
  doi = {10.1007/978-3-319-30307-9_3}
}

CP-nets have proven to be an effective representation for capturing preferences. However, their use in automated negotiation is not straightforward because, typically, preferences in CP-nets are partially ordered and negotiating agents are required to compare any two outcomes based on a request and an offer in order to negotiate effectively. If agents know how to generate total orders from their CP-nets, they can make this comparison. This paper proposes heuristics that enable the use of CP-nets in utility-based negotiations by generating total orderings. To validate this approach, the paper compares the performance of CP-nets with our heuristics with the performance of UCP-nets that are equipped with complete preference orderings. Our results show that we can achieve comparable performance in terms of the outcome utility. More importantly, one of our proposed heuristics can achieve this performance with significantly smaller number of interactions compared to UCP-nets.

@article{Ayd14,
  author = {Aydo\u{g}an, Reyhan and Baarslag, Tim and Hindriks, Koen V. and Jonker, Catholijn M. and Yolum, P{\i}nar},
  title = {Heuristics for Using CP-nets in Utility-based Negotiation Without Knowing Utilities},
  journal = {Knowledge and Information Systems},
  publisher = {Springer-Verlag New York, Inc.},
  month = {November},
  year = {2015},
  volume = {45},
  number = {2},
  pages = {357--388},
  issn = {0219-1377},
  address = {New York, NY, USA},
  url = {http://dx.doi.org/10.1007/s10115-014-0798-z},  
  doi = {10.1007/s10115-014-0798-z},
  keywords = {Automated negotiation, CP-nets, Heuristic-based approaches, Qualitative preferences}
}

CP-Nets have proven to be an effective representation for capturing preferences. However, their use in multiagent negotiation is not straightforward. The main reason for this is that CP-Nets capture partial ordering of preferences, whereas negotiating agents are required to compare any two outcomes based on the request and offers. This makes it necessary for agents to generate total orders from their CP-Nets. We have previously proposed a heuristic to generate total orders from a given CP-Net. This paper proposes another heuristic based on Borda count, applies it in negotiation, and compares its performance with the previous heuristic.

@inproceedings{Ayd11,
  author = {Reyhan Aydo{\u{g}}an and Tim Baarslag and Koen V. Hindriks and Catholijn M. Jonker and P{\i}nar Yolum},
  title = {Heuristic-based Approaches for CP-Nets in Negotiation},
  booktitle = {Complex Automated Negotiations: Theories, Models, and Software Competitions},
  publisher = {Springer Berlin Heidelberg},
  year = {2013},
  volume = {435},
  pages = {113-123},  
  series = {Studies in Computational Intelligence},
  editor = {Ito, Takayuki and Zhang, Minjie and Robu, Valentin and Matsuo, Tokuro},
  url = {http://dx.doi.org/10.1007/978-3-642-30737-9\_7},  
  doi = {10.1007/978-3-642-30737-9\_7}
}

Given the growing interest in automated negotiation, the search for effective strategies has produced a variety of different negotiation agents. Despite their diversity, there is a common structure to their design. A negotiation agent comprises three key components: the bidding strategy, the opponent model and the acceptance criteria. We show that this three-component view of a negotiating architecture not only provides a useful basis for developing such agents but also provides a useful analytical tool. By combining these components in varying ways, we are able to demonstrate the contribution of each component to the overall negotiation result, and thus determine the key contributing components. Moreover, we are able to study the interaction between components and present detailed interaction effects. Furthermore, we find that the bidding strategy in particular is of critical importance to the negotiator's success and far exceeds the importance of opponent preference modeling techniques. Our results contribute to the shaping of a research agenda for negotiating agent design by providing guidelines on how agent developers can spend their time most effectively.

@inproceedings{BaarslagComponentAnalysis,
  author = {Tim Baarslag and Alexander S.Y. Dirkzwager and Koen V. Hindriks and Catholijn M. Jonker},
  title = {The Significance of Bidding, Accepting and Opponent Modeling in Automated Negotiation},
  booktitle = {21st European Conference on Artificial Intelligence},
  publisher = {IOS Press},
  year = {2014},
  volume = {263},
  pages = {27-32},  
  series = {Frontiers in Artificial Intelligence and Applications},
  address = {Prague},
  url = {http://ebooks.iospress.nl/volumearticle/36911},  
  doi = {10.3233/978-1-61499-419-0-27}
}

This paper describes the PhD research topic of the author on designing an automated negotiator. One of the key challenges of designing a successful negotiation agent is that usually only limited information is available about the other party. Therefore, we need to combine various learning techniques to decide what offers to make, and when to accept. The research goal is to investigate techniques for developing a versatile automated negotiator that can effectively conduct negotiations in an incomplete information setting.

@inproceedings{Baarslag13AAMASDC,
  author = {Tim Baarslag},
  title = {Designing an Automated Negotiator: Learning What to Bid and when to Stop},
  booktitle = {Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  year = {2013},
  pages = {1419--1420},  
  series = {AAMAS '13},
  address = {Richland, SC},
  url = {http://dl.acm.org/citation.cfm?id=2485255},
  keywords = {artificial intelligence, machine learning, negotiation}
}

This paper presents an in-depth analysis and the key insights gained from the Second International Automated Negotiating Agents Competition (ANAC 2011). ANAC is an international competition that challenges researchers to develop successful automated negotiation agents for scenarios where there is no information about the strategies and preferences of the opponents. The key objectives of this competition are to advance the state-of-the-art in the area of practical bilateral multi-issue negotiations, and to encourage the design of agents that are able to operate effectively across a variety of scenarios. Eighteen teams from seven different institutes competed. This paper describes these agents, the setup of the tournament, including the negotiation scenarios used, and the results of both the qualifying and final rounds of the tournament. We then go on to analyse the different strategies and techniques employed by the participants using two methods: (i) we classify the agents with respect to their concession behaviour against a set of standard benchmark strategies and (ii) we employ empirical game theory (EGT) to investigate the robustness of the strategies. Our analysis of the competition results allows us to highlight several interesting insights for the broader automated negotiation community. In particular, we show that the most adaptive negotiation strategies, while robust across different opponents, are not necessarily the ones that win the competition. Furthermore, our EGT analysis highlights the importance of considering metrics, in addition to utility maximisation (such as the size of the basin of attraction), in determining what makes a successful and robust negotiation agent for practical settings.

@article{Baarslag12ANAC2011,
  author = {Tim Baarslag and Katsuhide Fujita and Enrico H. Gerding and Koen V. Hindriks and Takayuki Ito and Nicholas R. Jennings and Catholijn M. Jonker and Sarit Kraus and Raz Lin and Valentin Robu and Colin R. Williams},
  title = {Evaluating practical negotiating agents: Results and analysis of the 2011 international competition},
  journal = {Artificial Intelligence},
  publisher = {Elsevier Science Publishers Ltd.},
  month = {May},
  year = {2013},
  volume = {198},
  pages = {73 - 103},
  issn = {0004-3702},
  address = {Essex, UK},
  url = {http://dx.doi.org/10.1016/j.artint.2012.09.004},  
  doi = {10.1016/j.artint.2012.09.004}
}

An important aim in bilateral negotiations is to achieve a win-win solution for both parties; therefore, a critical aspect of a negotiating agent's success is its ability to take the opponent's preferences into account. Every year, new negotiation agents are introduced with better learning techniques to model the opponent. Our main goal in this work is to evaluate and compare the performance of a selection of state-of-the-art online opponent modeling techniques in negotiation, and to determine under which circumstances they are beneficial in a real-time, online negotiation setting. Towards this end, we provide an overview of the factors influencing the quality of a model and we analyze how the performance of opponent models depends on the negotiation setting. This results in better insight into the performance of opponent models, and allows us to pinpoint well-performing opponent modeling techniques that did not receive much previous attention in literature.

@inproceedings{Baarslag12AI,
  author = {Tim Baarslag and Mark J.C. Hendrikx and Koen V. Hindriks and Catholijn M. Jonker},
  title = {Measuring the Performance of Online Opponent Models in Automated Bilateral Negotiation},
  booktitle = {AI 2012: Advances in Artificial Intelligence},
  publisher = {Springer Berlin Heidelberg},
  year = {2012},
  volume = {7691},
  pages = {1--14},  
  series = {Lecture Notes in Computer Science},
  address = {Heidelberg},
  editor = {Michael Thielscher and Dongmo Zhang},
  url = {http://dx.doi.org/10.1007/978-3-642-35101-3_1},  
  doi = {10.1007/978-3-642-35101-3_1},
  keywords = {Negotiation; Opponent Model Performance; Quality Measures}
}

When two agents settle a mutual concern by negotiating with each other,they usually do not share their preferences so as to avoid exploitation. In such a setting, the agents may need to analyze each other's behavior to make an estimation of the opponent's preferences. This process of opponent modeling makes it possible to find a satisfying negotiation outcome for both parties. A large number of such opponent modeling techniques have already been introduced, together with different measures to assess their quality. The quality of an opponent model can be measured in two different ways: one is to use the agent's performance as a benchmark for the model's quality, the other is to directly evaluate its accuracy by using similarity measures. Both methods have been used extensively, and both have their distinct advantages and drawbacks. In this work we investigate the exact relation between the two, and we pinpoint the measures for accuracy that best predict performance gain. This leads us to new insights in how to construct an opponent model, and what we need to measure when optimizing performance.

@inproceedings{Baarslag13AIT,
  author = {Baarslag, Tim and Hendrikx, Mark J.C. and Hindriks, Koen V. and Jonker, Catholijn M.},
  title = {Predicting the Performance of Opponent Models in Automated Negotiation},
  booktitle = {Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)},
  publisher = {IEEE Computer Society},
  month = {Nov},
  year = {2013},
  volume = {2},
  pages = {59-66},  
  series = {WI-IAT '13},
  address = {Washington, DC, USA},
  url = {http://dx.doi.org/10.1109/WI-IAT.2013.91},  
  doi = {10.1109/WI-IAT.2013.91},
  keywords = {Intelligent agents, Multiagent systems, Machine learning}
}

Every year, automated negotiation agents are improving on various domains. However, given a set of automated negotiation agents, current methods allow to determine which strategy is best in terms of utility, but not so much the reason of success. In order to study the performance of the individual components of a negotiation strategy, we introduce an architecture that distinguishes three components which together constitute a negotiation strategy: the bidding strategy, the opponent model, and the acceptance strategy. Our contribution to the field of bilateral negotiation is twofold: first, we show that existing state-of-the-art agents are compatible with this architecture by re-implementing them in the new framework; secondly, as an application of our architecture, we systematically explore the space of possible strategies by recombining different strategy components, resulting in negotiation strategies that improve upon the current state-of-the-art in automated negotiation.

@incollection{BaarslagBOA,
  author = {Tim Baarslag and Koen V. Hindriks and Mark J.C. Hendrikx and Alex S.Y. Dirkzwager and Catholijn M. Jonker},
  title = {Decoupling Negotiating Agents to Explore the Space of Negotiation Strategies},
  booktitle = {Novel Insights in Agent-based Complex Automated Negotiation},
  publisher = {Springer, Japan},
  year = {2014},
  volume = {535},
  pages = {61-83},  
  series = {Studies in Computational Intelligence},
  editor = {Marsa-Maestre, Ivan and Lopez-Carmona, Miguel A. and Ito, Takayuki and Zhang, Minjie and Bai, Quan and Fujita, Katsuhide},
  url = {http://dx.doi.org/10.1007/978-4-431-54758-7\_4},  
  doi = {10.1007/978-4-431-54758-7\_4},
  keywords = {Acceptance condition; Automated bilateral negotiation; Bidding strategy; BOA architecture; Component-based; Opponent model}
}

Every year, automated negotiation agents are improving on various domains. However, given a set of automated negotiation agents, current methods allow to determine which strategy is best in terms of utility, but not so much the reason of success. In order to study the performance of the individual components of a negotiation strategy, we introduce an architecture that distinguishes three components which together constitute a negotiation strategy: the bidding strategy, the opponent model, and the acceptance strategy. Our contribution to the field of bilateral negotiation is twofold: first, we show that existing state-of-the-art agents are compatible with this architecture by re-implementing them in the new framework; secondly, as an application of our architecture, we systematically explore the space of possible strategies by recombining different strategy components, resulting in negotiation strategies that improve upon the current state-of-the-art in automated negotiation.

@inproceedings{Baarslag12ACAN,
  author = {Tim Baarslag and Koen V. Hindriks and Mark J.C. Hendrikx and Alex S.Y. Dirkzwager and Catholijn M. Jonker},
  title = {Decoupling Negotiating Agents to Explore the Space of Negotiation Strategies},
  booktitle = {Proceedings of The Fifth International Workshop on Agent-based Complex Automated Negotiations (ACAN 2012)},
  year = {2012},
  url = {http://ii.tudelft.nl/sites/default/files/boa.pdf}
}

We describe the strategy of our negotiating agent, Nice Tit for Tat Agent, which reached the finals of the 2011 Automated Negotiating Agent Competition. It uses a Tit for Tat strategy to select its offers in a negotiation, i.e.: initially it cooperates with its opponent, and in the following rounds of negotiation, it responds in kind to the opponent’s actions.We give an overview of how to implement such a Tit for Tat strategy and discuss its merits in the setting of closed bilateral negotiation.

@incollection{ANAC2011Baa,
  author = {Baarslag, Tim and Hindriks, Koen V. and Jonker, Catholijn M.},
  title = {A Tit for Tat Negotiation Strategy for Real-Time Bilateral Negotiations},
  booktitle = {Complex Automated Negotiations: Theories, Models, and Software Competitions},
  publisher = {Springer Berlin Heidelberg},
  year = {2013},
  volume = {435},
  pages = {229-233},  
  series = {Studies in Computational Intelligence},
  editor = {Ito, Takayuki and Zhang, Minjie and Robu, Valentin and Matsuo, Tokuro},
  url = {http://dx.doi.org/10.1007/978-3-642-30737-9\_18},  
  doi = {10.1007/978-3-642-30737-9\_18}
}

In every negotiation with a deadline, one of the negotiating parties has to accept an offer to avoid a break off. A break off is usually an undesirable outcome for both parties, therefore it is important that a negotiator employs a proficient mechanism to decide under which conditions to accept. When designing such conditions one is faced with the acceptance dilemma: accepting the current offer may be suboptimal, as better offers may still be presented. On the other hand, accepting too late may prevent an agreement from being reached, resulting in a break off with no gain for either party. Motivated by the challenges of bilateral negotiations between automated agents and by the results and insights of the automated negotiating agents competition (ANAC), we classify and compare state-of-the-art generic acceptance conditions. We focus on decoupled acceptance conditions, i.e. conditions that do not depend on the bidding strategy that is used. We performed extensive experiments to compare the performance of acceptance conditions in combination with a broad range of bidding strategies and negotiation domains. Furthermore we propose new acceptance conditions and we demonstrate that they outperform the other conditions that we study. In particular, it is shown that they outperform the standard acceptance condition of comparing the current offer with the offer the agent is ready to send out. We also provide insight in to why some conditions work better than others and investigate correlations between the properties of the negotiation environment and the efficacy of acceptance conditions.

@inproceedings{Baarslag11ACAN,
  author = {Tim Baarslag and Koen V. Hindriks and Catholijn M. Jonker},
  title = {Acceptance Conditions in Automated Negotiation},
  booktitle = {Complex Automated Negotiations: Theories, Models, and Software Competitions},
  publisher = {Springer Berlin Heidelberg},
  year = {2013},
  volume = {435},
  pages = {95-111},  
  series = {Studies in Computational Intelligence},
  editor = {Ito, Takayuki and Zhang, Minjie and Robu, Valentin and Matsuo, Tokuro},
  url = {http://dx.doi.org/10.1007/978-3-642-30737-9\_6},  
  doi = {10.1007/978-3-642-30737-9\_6}
}

In order to successfully reach an agreement in a negotiation, both parties rely on each other to make concessions. The willingness to concede also depends in large part on the opponent. A concession by the opponent may be reciprocated, but the negotiation process may also be frustrated if the opponent does not concede at all. This process of concession making is a central theme in many of the classic and current automated negotiation strategies. In this paper, we present a quantitative classification method of negotiation strategies that measures the willingness of an agent to concede against different types of opponents. The method is then applied to classify some well-known negotiating strategies, including the agents of ANAC 2010. It is shown that the technique makes it easy to identify the main characteristics of negotiation agents, and can be used to group negotiation strategies into categories with common negotiation characteristics. We also observe, among other things, that different kinds of opponents call for a different approach in making concessions.

@inproceedings{Baarslag11PRIMA,
  author = {Baarslag, Tim and Hindriks, Koen V. and Jonker, Catholijn M.},
  title = {Towards a Quantitative Concession-Based Classification Method of Negotiation Strategies},
  booktitle = {Agents in Principle, Agents in Practice},
  publisher = {Springer Berlin Heidelberg},
  year = {2011},
  volume = {7047},
  pages = {143--158},  
  series = {Lecture Notes in Computer Science},
  address = {Berlin, Heidelberg},
  editor = {Kinny, David and Hsu, Jane Yung-jen and Governatori, Guido and Ghose, Aditya K.},
  url = {http://dx.doi.org/10.1007/978-3-642-25044-6_13},  
  doi = {http://dx.doi.org/10.1007/978-3-642-25044-6\_13},
  keywords = {automated bilateral negotiation, classification, competition, concession, cooperation, negotiation strategy}
}

In May 2011, we organized the Second International Automated Negotiating Agents Competition (ANAC2011) in conjunction with AAMAS 2011. ANAC is an international competition that challenges researchers to develop a successful automated negotiator for scenarios where there is incomplete information about the opponent. One of the goals of this competition is to help steer the research in the area of bilateral multi-issue negotiations, and to encourage the design of generic negotiating agents that are able to operate in a variety of scenarios. Eighteen teams from seven different institutes competed in ANAC2011. This chapter describes the participating agents and the setup of the tournament, including the different negotiation scenarios that were used in the competition. We report on the results of the qualifying and final round of the tournament.

@incollection{ANAC2011Kawpaper,
  author = {Fujita, Katsuhide and Ito, Takayuki and Baarslag, Tim and Hindriks, Koen V. and Jonker, Catholijn M. and Kraus, Sarit and Lin, Raz},
  title = {The Second Automated Negotiating Agents Competition (ANAC 2011)},
  booktitle = {Complex Automated Negotiations: Theories, Models, and Software Competitions},
  publisher = {Springer Berlin Heidelberg},
  year = {2013},
  volume = {435},
  pages = {183-197},  
  series = {Studies in Computational Intelligence},
  editor = {Ito, Takayuki and Zhang, Minjie and Robu, Valentin and Matsuo, Tokuro},
  url = {http://dx.doi.org/10.1007/978-3-642-30737-9\_11}
}