- 1、本文档共18页,可阅读全部内容。
- 2、有哪些信誉好的足球投注网站(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)。
- 5、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 6、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 7、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 8、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
Lossy Stochastic Game Abstraction with Bounds
Tuomas Sandholm, Computer Science Department, Carnegie Mellon University
Satinder Singh, Computer Science Engineering, University of Michigan
Abstraction followed by equilibrium finding has emerged as the leading approach to solving games. Lossless
abstraction typically yields games that are still too large to solve, so lossy abstraction is needed. Unfor-
tunately, prior lossy game abstraction algorithms have no guarantees on solution quality. We developed a
framework that enables the design of lossy game abstraction algorithms with guarantees on solution qual-
ity. It simultaneously handles state and action abstraction. We define a measure of reward approximation
error and transition probability error achieved by state and action abstraction in stochastic games such that
the regret of the equilibrium found in the abstract game when implemented in the original, unabstracted
game is upper-bounded by a function of those measures. We then develop the first lossy game abstraction
algorithms with bounds on solution quality. Both of them work level-by-level up from the end of the game.
One of the algorithms is greedy and the other is an integer linear program. We also prove that the abstrac-
tion problem is NP-complete (even with just action abstraction, 2 agents, and a 1-step game), but point out
that this does not mean that the game abstraction problems that occur in practice cannot be solved quickly.
Categories and Subject Descriptors: I.2.11 [Distributed Artificial Intelligence]: Multiagent Systems; J.4
[Social and Behavioral Sciences]: Economics; I.2.1 [Artificial intelligence]: Applications and Expert
Systems: Games
General Terms: Algorithms, economics, theory
Additional Key Words and Phrases: Equilibrium finding, abstraction, game abstraction, computational game
theory, game solving, -equilibrium
1. INTRODUCTION
Game-theoretic solution (equilibrium) concepts provide a rigorous definitio
您可能关注的文档
- Lobbying and regulation in a strongpolitical economystrong Evidence from.pdf
- Local and Global Algorithms for Disambiguation to strongWikipediastrong.pdf
- LOCAL COMMUNITIES ATTITUDES TOWARDS IMPACTS OF TOURISM.pdf
- Local electronic properties of AlGaNGaN heterostructures.pdf
- Local government debt and strongeconomicstrong growth in China - SUOMEN.pdf
- Local participation in Indonesia’s Urban strongInfrastructurestrong.pdf
- Local Search and the Traveling Salesman Problem A Feature.pdf
- Local strongProtectionismstrong and Regional Specialization Evidence from.pdf
- Local strongRstrong&D Strategies and Multi-location Firms The Role of.pdf
- Local strongTreatmentstrong of HPV-Induced Skin Lesions by Cidofovir.pdf
文档评论(0)