Timezone: »

 
Spotlight
Near-Optimal Learning of Extensive-Form Games with Imperfect Information
Yu Bai · Chi Jin · Song Mei · Tiancheng Yu

Wed Jul 20 08:45 AM -- 08:50 AM (PDT) @ Room 310
in T: Game Theory/RL/Planning »
This paper resolves the open question of designing near-optimal algorithms for learning imperfect-information extensive-form games from bandit feedback. We present the first line of algorithms that require only $\widetilde{\mathcal{O}}((XA+YB)/\varepsilon^2)$ episodes of play to find an $\varepsilon$-approximate Nash equilibrium in two-player zero-sum games, where $X,Y$ are the number of information sets and $A,B$ are the number of actions for the two players. This improves upon the best known sample complexity of $\widetilde{\mathcal{O}}((X^2A+Y^2B)/\varepsilon^2)$ by a factor of $\widetilde{\mathcal{O}}(\max\{X, Y\})$, and matches the information-theoretic lower bound up to logarithmic factors. We achieve this sample complexity by two new algorithms: Balanced Online Mirror Descent, and Balanced Counterfactual Regret Minimization. Both algorithms rely on novel approaches of integrating \emph{balanced exploration policies} into their classical counterparts. We also extend our results to learning Coarse Correlated Equilibria in multi-player general-sum games.
Keywords: RL: Multi-agent · T: Game Theory · T: Online Learning and Bandits · T: Reinforcement Learning and Planning

Author Information

Yu Bai (Salesforce Research)
Chi Jin (Princeton University)
Song Mei (UC Berkeley)
Tiancheng Yu (MIT)

I am quant researcher at Two Sigma. I completed my PhD in MIT EECS in 2023.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors