Jihun Yun, Peng Zheng, et al.
ICML 2019
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 , a significant improvement over the 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 -approximate (coarse) correlated equilibria in full-information general-sum Markov games within iterations. Numerical results are also included to corroborate our theoretical findings.
Jihun Yun, Peng Zheng, et al.
ICML 2019
S. Winograd
Journal of the ACM
Ken C.L. Wong, Satyananda Kashyap, et al.
Pattern Recognition Letters
Alain Vaucher, Philippe Schwaller, et al.
AMLD EPFL 2022