Solving Games with Functional Regret Estimation [article]

Kevin Waugh and Dustin Morrill and J. Andrew Bagnell and Michael Bowling
2014 arXiv   pre-print
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
more » ... 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.
arXiv:1411.7974v2 fatcat:57tt42ntbbcvdlqt2jsuqdjway