- 1、本文档共31页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Journal of Machine Learning Research 4 (2003) 1039-1069 Submitted 11/01; Revised 10/02; Published 11/03
Nash Q-Learning for General-Sum Stochastic Games
Junling Hu JUNLING @TALKAI .COM
Talkai Research
843 Roble Ave., 2
Menlo Park, CA 94025, USA
Michael P. Wellman WELLMAN @UMICH .EDU
Artificial Intelligence Laboratory
University of Michigan
Ann Arbor, MI 48109-2110, USA
Editor: Craig Boutilier
Abstract
We extend Q-learning to a noncooperative multiagent context, using the framework of general-
sum stochastic games. A learning agent maintains Q-functions over joint actions, and performs
updates based on assuming Nash equilibrium behavior over the current Q-values. This learning
protocol provably converges given certain restrictions on the stage games (defined by Q-values) that
arise during learning. Experiments with a pair of two-player grid games suggest that such restric-
tions on the game structure are not necessarily required. Stage games encountered during learning
in both grid environments violate the conditions. However, learning consistently converges in the
first grid game, which has a unique equilibrium Q-function, but sometimes fails to converge in
the second, which has three different equilibrium Q-functions. In a comparison of offline learn-
ing performance in both games, we find agents are more likely to reach a joint optimal path with
Nash Q-learning than with a single-agent Q-learning method. When at least one agent adopts Nash
Q-learning, the performance of both agents is better than using single-agent Q-learning. We have
also implemented an online version of Nash Q-learning th
您可能关注的文档
- Multistate Point-Prevalence Survey of Health Care–Associated.pdf
- Multistep Synthesis of a Radiolabeled Imaging Probe Using.pdf
- Multiuser MIMO in Distributed Antenna Systems.pdf
- Multivariate GARCH models - S-WoPEc.pdf
- Multivariate Out-of-Sample Tests for Granger Causality.pdf
- Munich Personal RePEc Archive - mpra.ub.uni-muenchen.de.pdf
- Munich Personal RePEc Archive - uni-muenchen.de.pdf
- Munich Personal RePEc strongArchivestrong - mpra.ub.uni-muenchen.de.pdf
- Munich Personal RePEc strongArchivestrong - uni-muenchen.de.pdf
- Music training for the development of auditory skills.pdf
- 分析let s单元56ago2卷纸zheng unit56.pdf
- 塑胶材料其它分类原料pa9t 12.pdf
- md16x16数字媒体切换器设备.pdf
- 者参考项目发起人学科类型单位序列承包商修订页代码顺序典型.pdf
- 届世界天然气大会阿姆斯特丹2006add10288.pdf
- 期测试记录表每周weekly g1g6 journeys tests level 6 lesson26.pdf
- modernize-whitepaper现代化您应用程序白皮书.pdf
- anybackup产品典型案例分析.pdf
- 约克金融工程课程tfeslide32.pdf
- 广州市妇女儿童医疗中心历份教学药历01tjy.pdf
文档评论(0)