An adversarial environment model for bounded rational agents in zero-sum interactions

Inon Zuckerman, Sarit Kraus, Jeffrey S. Rosenschein, Gal Kaminka

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Multiagent environments are often not cooperative nor collaborative; in many cases, agents have conflicting interests, leading to adversarial interactions. This paper presents a formal Adversarial Environment model for bounded rational agents operating in a zero-sum environment. In such environments, attempts to use classical utility-based search methods can raise a variety of difficulties (e.g., implicitly modeling the opponent as an omniscient utility maximizer, rather than leveraging a more nuanced, explicit opponent model). We define an Adversarial Environment by describing the mental states of an agent in such an environment. We then present behavioral axioms that are intended to serve as design principles for building such adversarial agents. We explore the application of our approach by analyzing log files of completed Connect-Four games, and present an empirical analysis of the axioms' appropriateness.

Original languageEnglish
Title of host publicationAAMAS'07 - Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems
Pages550-557
Number of pages8
DOIs
StatePublished - 2007
Externally publishedYes
Event6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS'07 - Honolulu, HI, United States
Duration: 14 May 200818 May 2008

Publication series

NameProceedings of the International Conference on Autonomous Agents

Conference

Conference6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS'07
Country/TerritoryUnited States
CityHonolulu, HI
Period14/05/0818/05/08

Keywords

  • Agents
  • Modal logic
  • Multiagent systems

Fingerprint

Dive into the research topics of 'An adversarial environment model for bounded rational agents in zero-sum interactions'. Together they form a unique fingerprint.

Cite this