Learning to achieve socially optimal solutions in general-sum games
Refereed conference paper presented and published in conference proceedings

替代計量分析
.

其它資訊
摘要During multi-agent interactions, robust strategies are needed to help the agents to coordinate their actions on efficient outcomes. A large body of previous work focuses on designing strategies towards the goal of Nash equilibrium under self-play, which can be extremely inefficient in many situations. On the other hand, apart from performing well under self-play, a good strategy should also be able to well respond against those opponents adopting different strategies as much as possible. In this paper, we consider a particular class of opponents whose strategies are based on best-response policy and also we target at achieving the goal of social optimality. We propose a novel learning strategy TaFSO which can effectively influence the opponent's behavior towards socially optimal outcomes by utilizing the characteristic of best-response learners. Extensive simulations show that our strategy TaFSO achieves better performance than previous work under both self-play and against the class of best-response learners. © 2012 Springer-Verlag.
著者Hao J., Leung H.-F.
會議名稱12th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2012
會議開始日03.09.2012
會議完結日07.09.2012
會議地點Kuching
會議國家/地區馬來西亞
出版年份2012
月份10
日期25
卷號7458 LNAI
出版社Springer Verlag
出版地Germany
頁次88 - 99
國際標準書號9783642326943
國際標準期刊號0302-9743
語言英式英語

上次更新時間 2020-14-10 於 02:06