Timezone: »

 
Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games
Yang Cai · Haipeng Luo · Chen-Yu Wei · Weiqiang Zheng

@
in The Many Facets of Preference-Based Learning »
Event URL: https://openreview.net/forum?id=6VWoOqSTi3 »
We revisit the problem of learning in two-player zero-sum Markov games, focusing on developing an algorithm that is *uncoupled*, *convergent*, and *rational*, with non-asymptotic convergence rates to Nash equilibrium. We start from the case of stateless matrix game with bandit feedback as a warm-up, showing an $\mathcal{O}(t^{-\frac{1}{8}})$ last-iterate convergence rate. To the best of our knowledge, this is the first result that obtains finite last-iterate convergence rate given access to only bandit feedback. We extend our result to the case of irreducible Markov games, providing a last-iterate convergence rate of $\mathcal{O}(t^{-\frac{1}{9+\varepsilon}})$ for any $\varepsilon>0$. Finally, we study Markov games without any assumptions on the dynamics, and show a *path convergence* rate, a new notion of convergence we define, of $\mathcal{O}(t^{-\frac{1}{10}})$. Our algorithm removes the synchronization and prior knowledge requirement of [Wei et al, 2021], which pursued the same goals as us for irreducible Markov games. Our algorithm is related to [Chen et al., 2021, Cen et al., 2021] and also builds on the entropy regularization technique. However, we remove their requirement of communications on the entropy values, making our algorithm entirely uncoupled.

Author Information

Yang Cai (Yale University)
Haipeng Luo (University of Southern California)
Chen-Yu Wei (University of Virginia)
Weiqiang Zheng (Yale University)

More from the Same Authors