Solving Games with Functional Regret Estimation
This work addresses the challenge of efficient strategy computation in large games for AI and game theory applications, representing an incremental improvement over existing abstraction methods.
The paper tackles the problem of minimizing regret in large extensive-form games by proposing an online learning method that uses a function approximator to estimate regrets, which is proven to converge to a Nash equilibrium in self-play. Empirically, it achieves higher quality strategies than state-of-the-art abstraction techniques given the same resources.
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 no-regret 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 self-play so long as the regrets are ultimately realizable by the function approximator. Our technique can be understood as a principled generalization of existing work on abstraction 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 abstraction techniques given the same resources.