Skip to yearly menu bar Skip to main content

Workshop: Workshop on Reinforcement Learning Theory

Invited Speaker: Christian Kroer: Recent Advances in Iterative Methods for Large-Scale Game Solving

Christian Kroer


Iterative methods for approximating zero-sum Nash equilibria in extensive-form games have been a core component of recent advances in superhuman poker AIs. In this talk, I will first give an optimization-oriented description of how these methods work. Then, I will discuss and contrast two recent results: First, the development of a new entropy-based regularization method for the decision spaces associated with extensive-form games, which is simultaneously simpler to analyze and has better theoretical properties than the current state of the art. Second, I will discuss new algorithms based on optimistic variants of regret matching and CFR, which lead to very strong practical performance, in spite of inferior theoretical guarantees.

This talk is based on joint work with Gabriele Farina and Tuomas Sandholm.