Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
Machine Learning
2020-06-11 v1 Machine Learning
Abstract
We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. We prove an upper bound on the number of calls to the generative models needed for MDP-GapE to identify a near-optimal action with high probability. This problem-dependent sample complexity result is expressed in terms of the sub-optimality gaps of the state-action pairs that are visited during exploration. Our experiments reveal that MDP-GapE is also effective in practice, in contrast with other algorithms with sample complexity guarantees in the fixed-confidence setting, that are mostly theoretical.
Cite
@article{arxiv.2006.05879,
title = {Planning in Markov Decision Processes with Gap-Dependent Sample Complexity},
author = {Anders Jonsson and Emilie Kaufmann and Pierre Ménard and Omar Darwiche Domingues and Edouard Leurent and Michal Valko},
journal= {arXiv preprint arXiv:2006.05879},
year = {2020}
}