Publications

• Sorted by Date • Classified by Publication Type • Classified by Research Category •

Sample-Efficient Policy Space Response Oracles with Joint Experience Best Response

Ariyan Bighashdel, Thiago Dias Simão, and Frans A. Oliehoek. Sample-Efficient Policy Space Response Oracles with Joint Experience Best Response. In Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2026.

Download

pdf [615.1kB]  

Abstract

Game theory provides a mathematical way to study the interaction between multiple decision makers. However, classical game-theoretic analysis is limited in scalability due to the large number of strategies, precluding direct application to more complex scenarios. This survey provides a comprehensive overview of a framework for large games, known as Policy Space Response Oracles (PSRO), which holds promise to improve scalability by focusing attention on sufficient subsets of strategies. We first motivate PSRO and provide historical context. We then focus on the strategy exploration problem for PSRO: the challenge of assembling effective subsets of strategies that still represent the original game well with minimum computational cost. We survey current research directions for enhancing the efficiency of PSRO, and explore the applications of PSRO across various domains. We conclude by discussing open questions and future research.

BibTeX Entry

@inproceedings{Bighashdel26AAMAS,
    title=      {Sample-Efficient Policy Space Response Oracles 
                 with Joint Experience Best Response}, 
    author=     {Ariyan Bighashdel and 
		 Sim\~{a}o, Thiago Dias and
                 Frans A. Oliehoek},
    booktitle = AAMAS26,
    year =      2026,
    month =     may,
    organization =      {IFAAMAS},
    keywords =   {refereed},
    abstract = {
        Game theory provides a mathematical way to study the interaction between
        multiple decision makers. However, classical game-theoretic analysis is
        limited in scalability due to the large number of strategies,
        precluding direct application to more complex scenarios. This survey
        provides a comprehensive overview of a framework for large games, known
        as Policy Space Response Oracles (PSRO), which holds promise to improve
        scalability by focusing attention on sufficient subsets of strategies.
        We first motivate PSRO and provide historical context. We then focus on
        the strategy exploration problem for PSRO: the challenge of assembling
        effective subsets of strategies that still represent the original game
        well with minimum computational cost. We survey current research
        directions for enhancing the efficiency of PSRO, and explore the
        applications of PSRO across various domains. We conclude by discussing
        open questions and future research.      
    }
}

Generated by bib2html.pl (written by Patrick Riley) on Wed Mar 04, 2026 22:15:52 UTC