Litcius/Paper detail

On the complexity of computing Markov perfect equilibrium in general-sum stochastic games

Xiaotie Deng, Ningyuan Li, David Mguni, Jun Wang, Yaodong Yang

2022National Science Review27 citationsDOIOpen Access PDF

Abstract

ABSTRACT Similar to the role of Markov decision processes in reinforcement learning, Markov games (also called stochastic games) lay down the foundation for the study of multi-agent reinforcement learning and sequential agent interactions. We introduce approximate Markov perfect equilibrium as a solution to the computational problem of finite-state stochastic games repeated in the infinite horizon and prove its PPAD-completeness. This solution concept preserves the Markov perfect property and opens up the possibility for the success of multi-agent reinforcement learning algorithms on static two-player games to be extended to multi-agent dynamic games, expanding the reign of the PPAD-complete class.

Topics & Concepts

Reinforcement learningMarkov decision processMarkov chainMarkov perfect equilibriumComputer scienceMathematical economicsCompleteness (order theory)Markov processClass (philosophy)Q-learningMathematical optimizationMathematicsTheoretical computer scienceArtificial intelligenceNash equilibriumMachine learningStatisticsMathematical analysisReinforcement Learning in RoboticsAdvanced Bandit Algorithms ResearchGame Theory and Applications
On the complexity of computing Markov perfect equilibrium in general-sum stochastic games | Litcius