Gal A. Kaminka's Publications

Sorted by DateClassified by Publication TypeClassified by TopicGrouped by Student (current)Grouped by Former Students

An Adversarial Environment Model for Bounded Rational Agents in Zero-Sum Interactions

Inon Zuckerman, Sarit Kraus, Jeffrey S. Rosenschein, and Gal A. Kaminka. An Adversarial Environment Model for Bounded Rational Agents in Zero-Sum Interactions. In Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-07), 2007.

Download

[PDF]159.4kB  

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.

Additional Information

BibTeX

@InProceedings{aamas07inon, 
  author = 	 {Inon Zuckerman and Sarit Kraus and Jeffrey S. Rosenschein and Gal A. Kaminka}, 
  title = 	 {An Adversarial Environment Model for Bounded Rational Agents in Zero-Sum Interactions}, 
  OPTcrossref =  {}, 
  OPTkey = 	 {}, 
  booktitle = AAMAS-07, 
  OPTpages = 	 {In press}, 
  year = 	 {2007}, 
  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. 
  }, 
  wwwnote = {}, 
  OPTeditor = 	 {}, 
  OPTvolume = 	 {}, 
  OPTnumber = 	 {}, 
  OPTseries = 	 {}, 
  OPTaddress = 	 {}, 
  OPTmonth = 	 {}, 
  OPTorganization = {}, 
  OPTpublisher = {}, 
  OPTannote = 	 {} 
} 

Generated by bib2html.pl (written by Patrick Riley ) on Sat Feb 24, 2018 00:31:02