Filtered Fictitious Play for Perturbed Observation Potential Games and Decentralised POMDPs
Archie C. Chapman, Simon A. Williamson, Nicholas R. Jennings

TL;DR
This paper introduces filtered fictitious play, an algorithm designed to handle noisy observations in potential games and Dec-POMDPs, demonstrating improved convergence and performance over existing methods in noisy environments.
Contribution
The paper develops filtered fictitious play to ensure convergence in noisy potential games and applies it to Dec-POMDPs, outperforming current solvers under observation noise.
Findings
Filtered fictitious play converges to Nash equilibrium despite observation noise.
The new method outperforms state-of-the-art Dec-POMDP solvers by 100% on average.
The approach is validated in a box pushing problem with noisy observations.
Abstract
Potential games and decentralised partially observable MDPs (Dec-POMDPs) are two commonly used models of multi-agent interaction, for static optimisation and sequential decisionmaking settings, respectively. In this paper we introduce filtered fictitious play for solving repeated potential games in which each player's observations of others' actions are perturbed by random noise, and use this algorithm to construct an online learning method for solving Dec-POMDPs. Specifically, we prove that noise in observations prevents standard fictitious play from converging to Nash equilibrium in potential games, which also makes fictitious play impractical for solving Dec-POMDPs. To combat this, we derive filtered fictitious play, and provide conditions under which it converges to a Nash equilibrium in potential games with noisy observations. We then use filtered fictitious play to construct a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGame Theory and Applications · Experimental Behavioral Economics Studies · Auction Theory and Applications
