Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games

Zixiang Chen, Dongruo Zhou, Quanquan Gu
Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:227-261, 2022.

Abstract

We study reinforcement learning for two-player zero-sum Markov games with simultaneous moves in the finite-horizon setting, where the transition kernel of the underlying Markov games can be parameterized by a linear function over the current state, both players’ actions and the next state. In particular, we assume that we can control both players and aim to find the Nash Equilibrium by minimizing the duality gap. We propose an algorithm Nash-UCRL based on the principle “Optimism-in-Face-of-Uncertainty”. Our algorithm only needs to find a Coarse Correlated Equilibrium (CCE), which is computationally efficient. Specifically, we show that Nash-UCRL can provably achieve an $\tilde{O}(dH\sqrt{T})$ regret, where $d$ is the linear function dimension, $H$ is the length of the game and $T$ is the total number of steps in the game. To assess the optimality of our algorithm, we also prove an $\tilde{\Omega}( dH\sqrt{T})$ lower bound on the regret. Our upper bound matches the lower bound up to logarithmic factors, which suggests the optimality of our algorithm.

Cite this Paper


BibTeX
@InProceedings{pmlr-v167-chen22d, title = {Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games}, author = {Chen, Zixiang and Zhou, Dongruo and Gu, Quanquan}, booktitle = {Proceedings of The 33rd International Conference on Algorithmic Learning Theory}, pages = {227--261}, year = {2022}, editor = {Dasgupta, Sanjoy and Haghtalab, Nika}, volume = {167}, series = {Proceedings of Machine Learning Research}, month = {29 Mar--01 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v167/chen22d/chen22d.pdf}, url = {https://proceedings.mlr.press/v167/chen22d.html}, abstract = {We study reinforcement learning for two-player zero-sum Markov games with simultaneous moves in the finite-horizon setting, where the transition kernel of the underlying Markov games can be parameterized by a linear function over the current state, both players’ actions and the next state. In particular, we assume that we can control both players and aim to find the Nash Equilibrium by minimizing the duality gap. We propose an algorithm Nash-UCRL based on the principle “Optimism-in-Face-of-Uncertainty”. Our algorithm only needs to find a Coarse Correlated Equilibrium (CCE), which is computationally efficient. Specifically, we show that Nash-UCRL can provably achieve an $\tilde{O}(dH\sqrt{T})$ regret, where $d$ is the linear function dimension, $H$ is the length of the game and $T$ is the total number of steps in the game. To assess the optimality of our algorithm, we also prove an $\tilde{\Omega}( dH\sqrt{T})$ lower bound on the regret. Our upper bound matches the lower bound up to logarithmic factors, which suggests the optimality of our algorithm.} }
Endnote
%0 Conference Paper %T Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games %A Zixiang Chen %A Dongruo Zhou %A Quanquan Gu %B Proceedings of The 33rd International Conference on Algorithmic Learning Theory %C Proceedings of Machine Learning Research %D 2022 %E Sanjoy Dasgupta %E Nika Haghtalab %F pmlr-v167-chen22d %I PMLR %P 227--261 %U https://proceedings.mlr.press/v167/chen22d.html %V 167 %X We study reinforcement learning for two-player zero-sum Markov games with simultaneous moves in the finite-horizon setting, where the transition kernel of the underlying Markov games can be parameterized by a linear function over the current state, both players’ actions and the next state. In particular, we assume that we can control both players and aim to find the Nash Equilibrium by minimizing the duality gap. We propose an algorithm Nash-UCRL based on the principle “Optimism-in-Face-of-Uncertainty”. Our algorithm only needs to find a Coarse Correlated Equilibrium (CCE), which is computationally efficient. Specifically, we show that Nash-UCRL can provably achieve an $\tilde{O}(dH\sqrt{T})$ regret, where $d$ is the linear function dimension, $H$ is the length of the game and $T$ is the total number of steps in the game. To assess the optimality of our algorithm, we also prove an $\tilde{\Omega}( dH\sqrt{T})$ lower bound on the regret. Our upper bound matches the lower bound up to logarithmic factors, which suggests the optimality of our algorithm.
APA
Chen, Z., Zhou, D. & Gu, Q.. (2022). Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games. Proceedings of The 33rd International Conference on Algorithmic Learning Theory, in Proceedings of Machine Learning Research 167:227-261 Available from https://proceedings.mlr.press/v167/chen22d.html.

Related Material