Solving Games with Functional Regret Estimation

We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosing a particular action. A noregret algorithm uses these estimates in place of the true regrets to define a sequence of policies. We prove the approach sound by providing a bound relating the quality of the function approximation and regret of the algorithm. A corollary being that the method is guaranteed to converge to a Nash equilibrium in selfplay so long as the regrets are ultimately realizable by the function approximator. Our technique can be understood as a principled generalization of existing work action in large games; in our work, both the abstraction as well as the equilibrium are learned during self-play. We demonstrate empirically the method achieves higher quality strategies than state-of-the-art ion techniques given the same resources.

• Type: Journal
• Year: 2015
• Where: AAAI
• Authors: Kevin Waugh, Dustin Morrill, James Andrew Bagnell, Michael H. Bowling
• Keywords: AAAI 2015, Intelligent Agents