Current browse context:
cs.GT
Change to browse by:
References & Citations
Computer Science > Computer Science and Game Theory
Title: $\widetilde{O}(T^{-1})$ Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
(Submitted on 2 Feb 2024 (v1), last revised 23 Apr 2024 (this version, v2))
Abstract: No-regret learning has a long history of being closely connected to game theory. Recent works have devised uncoupled no-regret learning dynamics that, when adopted by all the players in normal-form games, converge to various equilibrium solutions at a near-optimal rate of $\widetilde{O}(T^{-1})$, a significant improvement over the $O(1/\sqrt{T})$ rate of classic no-regret learners. However, analogous convergence results are scarce in Markov games, a more generic setting that lays the foundation for multi-agent reinforcement learning. In this work, we close this gap by showing that the optimistic-follow-the-regularized-leader (OFTRL) algorithm, together with appropriate value update procedures, can find $\widetilde{O}(T^{-1})$-approximate (coarse) correlated equilibria in full-information general-sum Markov games within $T$ iterations. Numerical results are also included to corroborate our theoretical findings.
Submission history
From: Weichao Mao [view email][v1] Fri, 2 Feb 2024 20:40:27 GMT (727kb,D)
[v2] Tue, 23 Apr 2024 05:40:37 GMT (730kb,D)
Link back to: arXiv, form interface, contact.