Abstract:
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.
copied = false, 2000);
">
@conference{Waugh-2015-17187,
author = {Kevin Waugh And Dustin Morrill And J. Andrew (Drew) Bagnell And Michael Bowling},
title = {Solving Games with Functional Regret Estimation},
booktitle = {Proceedings of 29th AAAI Conference on Artificial Intelligence (AAAI '15)},
year = {2015},
month = {January},
pages = {2138 - 2144},
}
author = {Kevin Waugh And Dustin Morrill And J. Andrew (Drew) Bagnell And Michael Bowling},
title = {Solving Games with Functional Regret Estimation},
booktitle = {Proceedings of 29th AAAI Conference on Artificial Intelligence (AAAI '15)},
year = {2015},
month = {January},
pages = {2138 - 2144},
}