author = {Julien PĂ©rolat and Bilal PIOT and Matthieu Geist and Bruno Scherrer and Olivier Pietquin},
title = {{Softened Approximate Policy Iteration for Markov Games}},
year = {2016},
booktitle = {{International Conference on Machine Learning (ICML)}},
url = {http://jmlr.org/proceedings/papers/v48/perolat16.html},
abstract = {This paper reports theoretical and empirical investigations on the use of quasi-Newton methods to minimize the Optimal Bellman Residual (OBR) of zero-sum two-player Markov Games. First, it reveals that state-of-the-art algorithms can be derived by the direct application of Newton's method to different norms of the OBR. More precisely, when applied to the norm of the OBR, Newton's method results in the Bellman Residual Minimization Policy Iteration (BRMPI) and, when applied to the norm of the Projected OBR (POBR), it results into the standard Least Squares Policy Iteration (LSPI) algorithm. Consequently, new algorithms are proposed, making use of quasi-Newton methods to minimize the OBR and the POBR so as to take benefit of enhanced empirical performances at low cost. Indeed, using a quasi-Newton method approach introduces slight modifications in term of coding of LSPI and BRMPI but improves significantly both the stability and the performance of those algorithms. These phenomena are illustrated on an experiment conducted on artificially constructed games called Garnets.}