About

Tim Baarslag is a Scientific Staff Member at CWI (Centrum Wiskunde & Informatica, the national research institute for Mathematics and Computer Science in the Netherlands) and an Assistant Professor at Utrecht University. He is a Visiting Associate Professor at Nagoya University of Technology and Visiting Fellow at the University of Southampton.

Tim Baarslag graduated from Utrecht University with a MSc in Mathematics and a BSc in Computer Science (both cum laude). He obtained his PhD (cum laude) from Delft University of Technology in 2014 on the topic of intelligent decision support systems for automated negotiation. Between 2014 and 2016, he was a Research Fellow in the Electronics and Computer Science Department of the University of Southampton, where he worked on negotiation techniques for obtaining meaningful consent.

Tim Baarslag studies intelligent and autonomous systems that can collaborate through the process of joint decision making. Practical applications include smart energy trading, the Internet of Things, trading platforms, autonomous vehicles, and digital privacy & security assistants. Tim Baarslag currently investigates how negotiation AI can learn to haggle on behalf of users as part of an NWO Veni grant, called Representing Users in a Negotiation. His research is featured in Science Magazine, Wired, and New Scientist. His research interests include agent-based negotiation, coordination and cooperation, preference elicitation, decision making under uncertainty.

Tim is the leading developer of Genius, a negotiation environment for the design and evaluation of automated negotiators. He is also an organizer of the annual International Automated Negotiating Agent Competition. Tim is a member of the ACM Future of Computing Academy for outstanding early career researchers. He serves as a PC member in top-level conferences such as AAAI and IJCAI, and as a reviewer in high-ranking journals such as Artificial Intelligence and JAAMAS. He is also an organizer of the Workshop on Conflict Resolution in Decision Making (COREDEMA 2016, 2017).

Prizes


Interested?

If you are interested in my research, please do reach out. I am also continually looking for (industry) collaborations, talented interns, master students, PhD students, and postdocs.

News

New

Postdoctoral Researcher (3yr) in Multi-Agent Negotiation at Centrum Wiskunde & Informatica (CWI), Amsterdam (new deadline: November 5th)

I have a vacancy for a talented Postdoctoral Researcher on the topic of Autonomous negotiation agents for online peer to peer trading. The aim of the vacant position is to develop fundamental and applicable solutions for agent negotiations within a new online trading platform.

One of the scientific challenges in this project will be to formulate long-term negotiation strategies that can strike partial deals with multiple partners under preference uncertainty, motivated by the challenge of autonomously representing a user in repeated many-to-many negotiations. The candidate would be embedded in the Intelligent and Autonomous Systems research group at Centrum Wiskunde & Informatica (CWI). Applications can be sent to apply@cwi.nl, with a preferred starting date of December 1, 2018. Please contact me for more information.

New

Interview for Communications of the ACM

I have been interviewed for the Association of Computing Machinery (ACM) about the Automated Negotiating Agents Competition (ANAC), which I helped organize in July during the International Joint Conference on Artificial Intelligence (IJCAI) in Stockholm, Sweden.

Science Talent 2018 nomination by New Scientist

I have been nominated as Science Talent 2018 by New Scientist Magazine. This prize is awarded annually to a young researcher with a high scientific and social impact, who reaches a broad audience through his or her outreach activities. Please consider voting for me!

Negotiation algorithms

I appear on the Dutch science show Focus to talk about negotiation algorithms and how computers can now help you buy a house.

Negotiation postdoc vacancy

We have an open postdoc vacancy at CWI Amsterdam. We are looking for a Postdoc on learning utility functions for Negotiation and Intelligent Control.

Computers that negotiate on our behalf

I wrote an article for the European Research Consortium for Informatics and Mathematics magazine on the challenges of computer negotiation on our behalf, and how new methods are being created at CWI towards solving this problem.

Lecture on automated negotiation online

I explain my research on automated negotiation in a 10 minute lecture for the 'Universiteit van Nederland' (in Dutch), which is a collaboration between universities and research institutes to collect lectures from the best Dutch scientists. I explain the future of computers that will be able to negotiate on our behalf, for instance when buying a house online or in autonomous driving.

Winner of the ERCIM Cor Baayen Young Research Award

I am happy to receive the 2017 ERCIM Cor Baayen Young Research Award. This prize is awarded yearly to a promising young researcher in computer science and applied mathematics and carries a prize of €5000. The prize is awarded by ERCIM, which is The European Research Consortium for Informatics and Mathematics. CWI is a member of ERCIM, and so is for example Fraunhofer and INRIA. Each year, each member institute can nominate two candidates for the Cor Baayen Award, and an ERCIM committee determines the winner.

Research featured in Wired

My research on automated negotiation is featured in an article in Wired Germany: How would a machine conduct our salary negotiations?.

People do not negotiate very well. Artificial intelligence, says Tim Baarslag, could do much better. He is working on a future in which AI will represent us in negotiations - whether on eBay or in politics... more

IJCAI paper featured in Science

Our IJCAI 2017 paper on the various challenges and applications for autonomous negotiation is featured in an article in Science: How artificial intelligence could negotiate better deals for humans.

Veni grant for Representing Users in Negotiation

I have been awarded a Veni grant for the project called Representing Users in a Negotiation (RUN): An Autonomous Negotiator Under Preference Uncertainty. The Veni grant provides highly promising young scientists with the opportunity to further elaborate their own ideas during a period of three years. Veni is part of the Talent Scheme by The Netherlands Organisation for Scientific Research (NWO).

The International Automated Negotiating Agents Competition 2017

The call for intended participation at ANAC 2017 is out. To be held in conjunction with the International Joint Conference on Artificial Intelligence (IJCAI-2017), in Melbourne, 19-25th August 2017.

Open access: survey on learning in negotiation

My survey on opponent learning in negotiation is available with full open access: Learning about the opponent in automated bilateral negotiation: a comprehensive survey of opponent modeling techniques.

CFP: The Tenth International Workshop on Agent-based Complex Automated Negotiations (ACAN2017)

The Tenth International Workshop on Agent-based Complex Automated Negotiations (ACAN2017) will be held in conjunction with the 16th International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2017).

Publications

Shantanu Chakraborty, Tim Baarslag and Michael Kaisers (2018). Energy Contract Settlements through Automated Negotiation in Residential Cooperatives, In 2018 IEEE International Conference on Smart Grid Communications (SmartGridComm). [URL

Download pdf

Abstract

@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 Smart Grid Communications (SmartGridComm)},
  year = {2018},  
  organization = {IEEE},
  url = {https://arxiv.org/abs/1807.10978}
}

Iliana Pappi, Tim Baarslag, Michael Kaisers and Nikolaos G. Paterakis (2018). An Uncertainty-Aware Online Planning Algorithm for the Sustainable Electrification of Festivals, In Smart Energy Systems and Technology (SEST) 2018.  

Download pdf

Abstract

@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 = {Smart Energy Systems and Technology (SEST) 2018},
  year = {2018}
}

Tim Baarslag (2018). Computers that negotiate on our behalf, ERCIM News.(112), pp. 36-37.  

Download pdf

Abstract
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}
}

Tim Baarslag, Michael Kaisers, Enrico H. Gerding, Catholijn M. Jonker and Jonathan Gratch (2017). Computers That Negotiate on Our Behalf: Major Challenges for Self-sufficient, Self-directed, and Interdependent Negotiating Agents, In Autonomous Agents and Multiagent Systems: AAMAS 2017 Workshops, Visionary Papers, São Paulo, Brazil, May 8-12, 2017, Revised Selected Papers. Cham Vol. 10643, pp. 143-163. Springer International Publishing. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Michael Kaisers, Enrico H. Gerding, Catholijn M. Jonker and Jonathan Gratch (2017). When will negotiation agents be able to represent us? The challenges and opportunities for autonomous negotiators, In Proceedings of the Twenty-sixth International Joint Conference on Artificial Intelligence. Melbourne, Australia, pp. 4684-4690. [URL]  [DOI]

Download pdf

Abstract
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}
}

Catholijn M. Jonker, Reyhan Aydoğan, Tim Baarslag, Joost Broekens, Christian A. Detweiler, Koen V. Hindriks, Alina Huldtgren and Wouter Pasman (2017). An Introduction to the Pocket Negotiator: A General Purpose Negotiation Support System, In 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. Cham Vol. 10207, pp. 13-27. Springer International Publishing. [URL]  [DOI]

Download pdf

Abstract
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}
}

Victor Sanchez-Anguix, Reyhan Aydoğan, Tim Baarslag and Catholijn M. Jonker (2017). Can We Reach Pareto Optimal Outcomes Using Bottom-Up Approaches?, In Conflict Resolution in Decision Making: Second International Workshop, COREDEMA 2016, The Hague, The Netherlands, August 29-30, 2016, Revised Selected Papers. Cham, pp. 19-35. Springer International Publishing. [URL]  [DOI]

Download pdf

Abstract
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}
}

Catholijn M. Jonker, Reyhan Aydoğan, Tim Baarslag, Katsuhide Fujita, Takayuki Ito and Koen Hindriks (2017). Automated Negotiating Agents Competition (ANAC), In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence and Twenty-Ninth Innovative Applications of Artificial Intelligence Conference., pp. 5070-5072. [URL

Download pdf

Abstract
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}
}

Edmon Begoli, Vincent Schlegel, Michael Atiyah, Praise Adeyemo and Tim Baarslag (2017). The Heidelberg Laureate Forum on the Moving Frontier Between Mathematics and Computer Science, XRDS. New York, NY, USA Vol. 23(3), pp. 46-49. ACM. [URL]  [DOI]

Download pdf

Abstract
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}
}

Katsuhide Fujita, Reyhan Aydoğan, Tim Baarslag, Koen Hindriks, Takayuki Ito and Catholijn Jonker (2017). The Sixth Automated Negotiating Agents Competition (ANAC 2015), In Modern Approaches to Agent-based Complex Automated Negotiation. Vol. 674, pp. 139-151. Springer. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Alper T. Alan, Richard Gomer, Mudasser Alam, Charith Perera, Enrico H. Gerding and M. C. Schraefel (2017). An Automated Negotiation Agent for Permission Management, In Proceedings of the 2017 International Conference on Autonomous Agents and Multi-agent Systems. Richland, SC, pp. 380-390. International Foundation for Autonomous Agents and Multiagent Systems. [URL

Download pdf

Abstract
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}
}

Tim Baarslag and Michael Kaisers (2017). The Value of Information in Automated Negotiation: A Decision Model for Eliciting User Preferences, In Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems. Richland, SC, pp. 391-400. International Foundation for Autonomous Agents and Multiagent Systems. [URL

Download pdf

Abstract
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}
}

Tim Baarslag, Mark J. C. Hendrikx, Koen V. Hindriks and Catholijn M. Jonker (2016). Learning about the opponent in automated bilateral negotiation: a comprehensive survey of opponent modeling techniques, Autonomous Agents and Multi-Agent Systems. Vol. 30(5), pp. 849-898. Springer US. [URL]  [DOI]

Download pdf

Abstract
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}
}

Charith Perera, Susan Y. L. Wakenshaw, Tim Baarslag, Hamed Haddadi, Arosha K. Bandara, Richard Mortier, Andy Crabtree, Irene C. L. Ng, Derek McAuley and Jon Crowcroft (2017). Valorising the IoT Databox: creating value for everyone, Transactions on Emerging Telecommunications Technologies. Vol. 28(1), pp. 1-17. John Wiley & Sons, Ltd. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag (2016). Exploring the Strategy Space of Negotiating Agents: A Framework for Bidding, Learning and Accepting in Automated Negotiation Springer International Publishing. [URL]  [DOI]

Download pdf

Abstract
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}
}

Ngoc Cuong Truong, Tim Baarslag, Gopal Ramchurn and Long Tran-Thanh (2016). Interactive scheduling of appliance usage in the home, In The 25th International Joint Conference on Artificial Intelligence. AAAI Press. [URL

Download pdf

Abstract
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/}
}

Shaofei Chen, Tim Baarslag, Dengji Zhao, Jing Chen and Lincheng Shen (2016). A polynomial time optimal algorithm for robot-human search under uncertainty, In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. New York, USA, pp. 819-825. AAAI Press. [URL

Download pdf

Abstract
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}
}

Tim Baarslag, Alper T. Alan, Richard C. Gomer, Ilaria Liccardi, Helia Marreiros, Enrico H. Gerding and M. C. Schraefel (2016). Negotiation As an Interaction Mechanism for Deciding App Permissions, In Proceedings of the 2016 CHI Conference: Extended Abstracts on Human Factors in Computing Systems. New York, NY, USA, pp. 2012-2019. ACM. [URL]  [DOI]

Download pdf

Abstract
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}
}

Reyhan Aydoğan, Tim Baarslag, Catholijn M. Jonker, Katsuhide Fujita, Takayuki Ito, Rafik Hadfi and Kohei Hayakawa (2016). A Baseline for Non-Linear Bilateral Negotiations: The full results of the agents competing in ANAC 2014, In Intelligent Computational Systems: A Multi-Disciplinary Perspective. Bentham Science Publishers. [URL

Download pdf

Abstract
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/}
}

Katsuhide Fujita, Reyhan Aydoğan, Tim Baarslag, Takayuki Ito and Catholijn Jonker (2016). The Fifth Automated Negotiating Agents Competition (ANAC 2014), In Recent Advances in Agent-based Complex Automated Negotiation. Cham Vol. 638, pp. 211-224. Springer International Publishing. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Mark J. C. Hendrikx, Koen V. Hindriks and Catholijn M. Jonker (2016). A Survey of Opponent Modeling Techniques in Automated Negotiation, In Proceedings of the 2016 International Conference on Autonomous Agents and Multi-agent Systems. Richland, SC, pp. 575-576. International Foundation for Autonomous Agents and Multiagent Systems. [URL

Download pdf

Abstract
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}
}

Tim Baarslag, Enrico H. Gerding, Reyhan Aydoğan and M. C. Schraefel (2015). Optimal Negotiation Decision Functions in Time-Sensitive Domains, In 2015 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT). Vol. 2, pp. 190-197. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Reyhan Aydoğan, Koen V. Hindriks, Katsuhide Fuijita, Takayuki Ito and Catholijn M. Jonker (2015). The Automated Negotiating Agents Competition, 2010-2015, AI Magazine. Vol. 36(4), pp. 115-118. Association for the Advancement of Artificial Intelligence (AAAI). [URL

Download pdf

Abstract
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}
}

Tim Baarslag and Enrico H. Gerding (2015). Optimal Incremental Preference Elicitation during Negotiation, In Proceedings of the Twenty-fourth International Joint Conference on Artificial Intelligence. Buenos Aires, Argentina, pp. 3-9. [URL

Download pdf

Abstract
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}
}

Tim Baarslag (2014). What to Bid and When to Stop Thesis at: Delft University of Technology. [URL]  [DOI]

Download pdf

Abstract
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}
}

Raz Lin, Sarit Kraus, Tim Baarslag, Dmytro Tykhonov, Koen V. Hindriks and Catholijn M. Jonker (2014). Genius: An Integrated Environment for Supporting the Design of Generic Automated Negotiators, Computational Intelligence. Vol. 30(1), pp. 48-70. Blackwell Publishing Inc. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks and Catholijn M. Jonker (2014). Effective Acceptance Conditions in Real-time Automated Negotiation, Decision Support Systems. Amsterdam, The Netherlands, The Netherlands Vol. 60, pp. 68-77. Elsevier Science Publishers B.V.. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks, Catholijn M. Jonker, Sarit Kraus and Raz Lin (2012). The First Automated Negotiating Agents Competition (ANAC 2010), In New Trends in Agent-based Complex Automated Negotiations. Berlin, Heidelberg Vol. 383, pp. 113-135. Springer-Verlag. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag and Koen V. Hindriks (2013). Accepting Optimally in Automated Negotiation with Incomplete Information, In Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems. Richland, SC, pp. 715-722. International Foundation for Autonomous Agents and Multiagent Systems. [URL

Download pdf

Abstract
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}
}

Tim Baarslag, Rafik Hadfi, Koen V. Hindriks, Takayuki Ito and Catholijn M. Jonker (2016). Optimal Non-adaptive Concession Strategies with Incomplete Information, In Recent Advances in Agent-based Complex Automated Negotiation. Cham Vol. 638, pp. 39-54. Springer International Publishing. [URL]  [DOI]

Download pdf

Abstract
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}
}

Reyhan Aydoğan, Tim Baarslag, Koen V. Hindriks, Catholijn M. Jonker and Pınar Yolum (2015). Heuristics for Using CP-nets in Utility-based Negotiation Without Knowing Utilities, Knowledge and Information Systems. New York, NY, USA Vol. 45(2), pp. 357-388. Springer-Verlag New York, Inc.. [URL]  [DOI]

Download pdf

Abstract
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}
}

Reyhan Aydoğan, Tim Baarslag, Koen V. Hindriks, Catholijn M. Jonker and Pınar Yolum (2013). Heuristic-based Approaches for CP-Nets in Negotiation, In Complex Automated Negotiations: Theories, Models, and Software Competitions. Vol. 435, pp. 113-123. Springer Berlin Heidelberg. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Alexander S. Y. Dirkzwager, Koen V. Hindriks and Catholijn M. Jonker (2014). The Significance of Bidding, Accepting and Opponent Modeling in Automated Negotiation, In 21st European Conference on Artificial Intelligence. Prague Vol. 263, pp. 27-32. IOS Press. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag (2013). Designing an Automated Negotiator: Learning What to Bid and when to Stop, In Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems. Richland, SC, pp. 1419-1420. International Foundation for Autonomous Agents and Multiagent Systems. [URL

Download pdf

Abstract
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}
}

Tim Baarslag, Katsuhide Fujita, Enrico H. Gerding, Koen V. Hindriks, Takayuki Ito, Nicholas R. Jennings, Catholijn M. Jonker, Sarit Kraus, Raz Lin, Valentin Robu and Colin R. Williams (2013). Evaluating practical negotiating agents: Results and analysis of the 2011 international competition, Artificial Intelligence. Essex, UK Vol. 198, pp. 73 - 103. Elsevier Science Publishers Ltd.. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Mark J. C. Hendrikx, Koen V. Hindriks and Catholijn M. Jonker (2012). Measuring the Performance of Online Opponent Models in Automated Bilateral Negotiation, In AI 2012: Advances in Artificial Intelligence. Heidelberg Vol. 7691, pp. 1-14. Springer Berlin Heidelberg. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Mark J. C. Hendrikx, Koen V. Hindriks and Catholijn M. Jonker (2013). Predicting the Performance of Opponent Models in Automated Negotiation, In Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT). Washington, DC, USA Vol. 2, pp. 59-66. IEEE Computer Society. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks, Mark J. C. Hendrikx, Alex S. Y. Dirkzwager and Catholijn M. Jonker (2014). Decoupling Negotiating Agents to Explore the Space of Negotiation Strategies, In Novel Insights in Agent-based Complex Automated Negotiation. Vol. 535, pp. 61-83. Springer, Japan. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks, Mark J. C. Hendrikx, Alex S. Y. Dirkzwager and Catholijn M. Jonker (2012). Decoupling Negotiating Agents to Explore the Space of Negotiation Strategies, In Proceedings of The Fifth International Workshop on Agent-based Complex Automated Negotiations (ACAN 2012). [URL

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks and Catholijn M. Jonker (2013). A Tit for Tat Negotiation Strategy for Real-Time Bilateral Negotiations, In Complex Automated Negotiations: Theories, Models, and Software Competitions. Vol. 435, pp. 229-233. Springer Berlin Heidelberg. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks and Catholijn M. Jonker (2013). Acceptance Conditions in Automated Negotiation, In Complex Automated Negotiations: Theories, Models, and Software Competitions. Vol. 435, pp. 95-111. Springer Berlin Heidelberg. [URL]  [DOI]

Download pdf

Abstract
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}
}

Tim Baarslag, Koen V. Hindriks and Catholijn M. Jonker (2011). Towards a Quantitative Concession-Based Classification Method of Negotiation Strategies, In Agents in Principle, Agents in Practice. Berlin, Heidelberg Vol. 7047, pp. 143-158. Springer Berlin Heidelberg. [URL]  [DOI]

Download pdf

Abstract
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}
}

Katsuhide Fujita, Takayuki Ito, Tim Baarslag, Koen V. Hindriks, Catholijn M. Jonker, Sarit Kraus and Raz Lin (2013). The Second Automated Negotiating Agents Competition (ANAC 2011), In Complex Automated Negotiations: Theories, Models, and Software Competitions. Vol. 435, pp. 183-197. Springer Berlin Heidelberg. [URL

Download pdf

Abstract
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}
}


(More publications following soon)

Frequently Asked Questions


What is automated negotiation?

Automated negotiation is a negotiation in which one of the actors is a computer. More precisely, negotiation is the process by which a group of actors (including at least one autonomous software agent) try to reach a mutually beneficial agreement.

What is negotiation?

Negotiation is the process of joint decision making. There are many alternative definitions, but this one neatly captures the emphasis on how to get to an agreement. Rather than describing what actions to perform, negotiation focuses on concessions, interlocution, and committments in order to influence the decisions of all actors involved.

What are the benefits of automated negotiation?

Automated negotiation research is fueled by a number of potential benefits, including better (win-win) deals, and reduction in time, costs, stress and cognitive effort on the part of users.

How can automated negotiation be used?

Negotiation arises in almost every social and organizational setting, yet many avoid it out of fear or lack of skill and this contributes to income inequality, political gridlock and social injustice. This has led to an increasing focus on the design of autonomous negotiators capable of automatically and independently negotiating with others. Computers that negotiate autonomously are rapidly emerging in a number of upcoming applications:

  • The smart electrical grid; where energy collectives trade complex energy contracts;
  • The Internet of Things; where billions of devices negotiate the usage of privacy-sensitive data;
  • Digital marketplaces; where goods are traded on platforms such as eBay, Funda, and Catawiki, or even on the fully decentralized world wide web of Blockstack;
  • Autonomous driving; where autonomous vehicles negotiate priority rules and exchange micro-tolling payments.

Q&A


I was interviewed by WIRED about automated negotiation. For the full article in WIRED Germany, see: How would a machine conduct our salary negotiations?

Why do we need the help of artificial intelligence when negotiating?

People are not very good negotiators. They reach sub-optimal results in different situations - for both negotiating partners. It is quite unfortunate if there exists an alternative agreement that would have been better for both.

Why is artificial intelligence better than us at negotiating?

People can only process a limited amount of information. But the possible outcomes of a negotiation are gigantic. For humans it is hard to get a good overview there. This leads to all sorts of cognitive biases that affect us. Another problem is the lack of preparation: we sometimes start directly with negotiating, without thinking about what we or our counterparts really want. This might be the reason that many people find negotiation very stressful.

What things are humans typically bad at in a negotiation?

A good example is the so-called "positional bargaining". So when I say, "I gave up something in this negotiation, so you have to give up something, too." But that does not really matter, because in the end it only counts what you get. Each of these problems could at least be mitigated by AI representatives. An artificial intelligence is rational enough to recognize all possible outcomes and it is not affected by emotions and cognitive bias.

What negotiations could AI do for me?

It could represent you in a salary negotiation or help you buy a house. If your mobile contract expires, a company might let you negotiate with an AI about your new contract - instead of someone calling you from a call center. The AI could also help in politics, where many things are settled in negotiations. I always find it astonishing that such extremely important political decisions do not use computers.

To represent me, the AI would need a pretty good idea of what I want.

This is a difficult problem. For this the computer would have to ask you a lot of questions - and that gets annoying quickly. If you have to answer too many questions, you can conduct the negotiation just as well yourself. So the question is: How can an AI negotiate well for you, even if it has limited information about you?

And how can AI negotiate for us with limited information?

The research community has not yet tackled this problem, but I am currently working on this. The question is: how do you get the AI to ask you the right questions at the right time? For instance, sometimes a question is simply not important. If you negotiate the contract conditions for a new job, your AI representative might want to know beforehand if you would like a company car. But perhaps this is not relevant at all because the company has no company cars. Then the AI should not ask you this question.

For this, the AI would have to understand exactly what is being negotiated.

Yes, if AI-Agents one day, for example, were to replace real estate agents, they must understand what a reasonable offer is. Real estate agents know a lot about the market, they know when a seller simply leaves because the offer is too low. The AI-real estate agents need this kind of information, too: What are possible offers, what is acceptable for the other side? I could imagine that it will be a job in the future to provide the AI representatives with this kind of information.

We often link negotiations with deception and lies. Can an AI do that too?

When one computer is negotiating with another, "deception" takes on a completely different meaning. Two computers can exchange thousands of offers instead of talking about what they want- they do not have to lie. Of course, one does not reveal all his information, but it is no longer as important as when two people negotiate with each other.

And what happens when a human and a machine negotiate with each other?

For people, lies and deceptions are still the norm - this is also one of the reasons why many people do not like to negotiate. They are afraid that they are not talented enough. But if this is the best strategy, an AI can also misrepresent the truth. We do not really teach it to lie, but the mathematical models show that you should not give all your information right at the beginning. An AI therefore does not always have to tell the truth.

Isn't that a problem for the trust? If I am not sure if my AI is representing me well, I do not want its help any more.

For this, it is important that the AI does not simply does its thing and then returns with the final result. In order to create trust, it has to ask now and then: "Is this what you had in mind? What would be your preference?" Another important aspect is transparency. That the AI communicates openly, what it thinks, for example, about your preferences and that of your negotiating partner. It could also give you an indication as to what the result will look like: "I think I can get this ebay item for 25 euros, and if it gets more expensive, I'll sign in again."

A lot of research is still needed before AI does all negotiations for us. Where do you see the first applications?

There are different areas that will need computer negotiations in the coming years. One example is the "smart grid", an intelligent electricity network that is used for energy trading. You can buy not only energy, but also sell it. Thse negotiations take place in such a short time that only computers can really handle them. These new, digital negotiations will soon be needed all over the world, conducted by AI negotiatiors.

Contact


Contact information

Tim Baarslag
Researcher
Room M358
Intelligent and Autonomous Systems group
Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands
Telephone: +31(0)20 592 4019
E-mail (Feel free to address me with "Dear Tim")

Profiles