Papers › Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

21 Sep 2023NeurIPS 2023 11archive 2025-07-28

This work studies an independent natural policy gradient (NPG) algorithm for the multi-agent reinforcement learning problem in Markov potential games. It is shown that, under mild technical assumptions and the introduction of the \textit{suboptimality gap}, the independent NPG method with an oracle providing exact policy evaluation asymptotically reaches an ϵ-Nash Equilibrium (NE) within 𝒪(1/ϵ) iterations. This improves upon the previous best result of 𝒪(1/ϵ²) iterations and is of the same order, 𝒪(1/ϵ), that is achievable for the single-agent case. Empirical results for a synthetic potential game and a congestion game are presented to verify the theoretical bounds.

PaperPDFCode

Code

sundave1998/independent-npg-mpg officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections