@inproceedings{jonsson2020planning,
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.},
author = {Jonsson, Anders and Kaufmann, Emilie and M{\'{e}}nard, Pierre and Domingues, Omar Darwiche and Leurent, Edouard and Valko, Michal},
booktitle = {Neural Information Processing Systems},
title = {{Planning in markov decision processes with gap-dependent sample complexity}},
year = {2020}
}