Planning in entropy-regularized Markov decision processes and games

Part of Advances in Neural Information Processing Systems 32 (NeurIPS 2019)

Authors

Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Menard, Remi Munos, Michal Valko

Abstract

We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player games, given a generative model of the SmoothCruiser. SmoothCruiser makes use of the smoothness of the Bellman operator promoted by the regularization to achieve problem-independent sample complexity of order $\tilde{\mathcal{O}}(1/\epsilon^4)$ for a desired accuracy $\epsilon$, whereas for non-regularized settings there are no known algorithms with guaranteed polynomial sample complexity in the worst case.