Global Convergence of Multi-Agent Policy Gradient in Markov Potential GamesDownload PDF

29 Sept 2021, 00:30 (edited 14 Mar 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: Multi-agent Reinforcement Learning, Markov Potential Games, Policy Gradient
  • Abstract: Potential games are arguably one of the most important and widely studied classes of normal form games. They define the archetypal setting of multi-agent coordination in which all agents utilities are perfectly aligned via a common potential function. Can this intuitive framework be transplanted in the setting of Markov games? What are the similarities and differences between multi-agent coordination with and without state dependence? To answer these questions, we study a natural class of Markov Potential Games (MPGs) that generalize prior attempts at capturing complex stateful multi-agent coordination. Counter-intuitively, insights from normal-form potential games do not carry over as MPGs involve settings where state-games can be zero-sum games. In the opposite direction, Markov games where every state-game is a potential game are not necessarily MPGs. Nevertheless, MPGs showcase standard desirable properties such as the existence of deterministic Nash policies. In our main technical result, we prove convergence of independent policy gradient and its stochastic counterpart to Nash policies (polynomially fast in the approximation error) by adapting recent gradient dominance property arguments developed for single-agent Markov decision processes to multi-agent learning settings.
  • One-sentence Summary: Convergence of policy gradient in a class of MDPs called Markov Potential Games in which cooperation is desired.
  • Supplementary Material: zip
10 Replies