Agent Competition, Agent-based Negotiation, Machine Learning
The Automated Negotiating Agents Competition (ANAC) is annually organized competition to facilitate the research on automated negotiation. This paper presents the ANAC 2017 Repeated Multilateral Negotiation League. As human negotiators do, agents are supposed to learn from their previous negotiations and improve their negotiation skills over time. Especially, when they negotiate with the same opponent on the same domain, they can adopt their negotiation strategy according to their past experiences. They can adjust their acceptance threshold or bidding strategy accordingly. In ANAC 2017, participants aimed to develop such a negotiating agent. Accordingly, this paper describes the competition settings and results with a brief description of the winner negotiation strategies.
Bibtex info
@inproceedings{aydogan_anac_2021,
address = {Singapore},
title = {{ANAC} 2017: {Repeated} {Multilateral} {Negotiation} {League}},
isbn = {978-981-15-5869-6},
abstract = {The Automated Negotiating Agents Competition (ANAC) is annually organized competition to facilitate the research on automated negotiation. This paper presents the ANAC 2017 Repeated Multilateral Negotiation League. As human negotiators do, agents are supposed to learn from their previous negotiations and improve their negotiation skills over time. Especially, when they negotiate with the same opponent on the same domain, they can adopt their negotiation strategy according to their past experiences. They can adjust their acceptance threshold or bidding strategy accordingly. In ANAC 2017, participants aimed to develop such a negotiating agent. Accordingly, this paper describes the competition settings and results with a brief description of the winner negotiation strategies.},
booktitle = {Advances in {Automated} {Negotiations}},
publisher = {Springer Singapore},
author = {Aydoğan, Reyhan and Fujita, Katsuhide and Baarslag, Tim and Jonker, Catholijn M. and Ito, Takayuki},
editor = {Ito, Takayuki and Zhang, Minjie and Aydoğan, Reyhan},
year = {2021},
pages = {101--115},
}