Independent Natural Policy Gradient Always Converges In Markov Potential Games

Abstract

Multi-agent reinforcement learning has been successfully applied to fully-cooperative and fully-competitive environments, but little is currently known about mixed cooperative/competitive environments. In this paper, we focus on a particular class of multi-agent mixed cooperative/competitive stochastic games called Markov Potential Games (MPGs), which include cooperative games as a special case. Recent results have shown that independent policy gradient converges in MPGs but it was not known whether Independent Natural Policy Gradient converges in MPGs as well. We prove that Independent Natural Policy Gradient always converges in the last iterate using constant learning rates. The proof deviates from the existing approaches and the main challenge lies in the fact that Markov Potential Games do not have unique optimal values (as single-agent settings exhibit) so different initializations can lead to different limit point values. We complement our theoretical results with experiments tha

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfox2021independent

Related papers

• Independent Policy Gradient For Large-scale Markov Potential Games: Sharper Rates, Function Approximation, And Game-agnostic Convergence (2022)0.00
• Provably Fast Convergence Of Independent Natural Policy Gradient For Markov Potential Games (2023)0.00
• Global Convergence Of Multi-agent Policy Gradient In Markov Potential Games (2021)0.00
• Independent Learning In Constrained Markov Potential Games (2024)0.00
• Convergence And Price Of Anarchy Guarantees Of The Softmax Policy Gradient In Markov Potential Games (2022)0.00
• On The Global Convergence Rates Of Decentralized Softmax Gradient Play In Markov Potential Games (2022)0.00
• Independent Policy Mirror Descent For Markov Potential Games: Scaling To Large Number Of Players (2024)0.00
• Independent And Decentralized Learning In Markov Potential Games (2022)0.00