Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
arXiv:2006.05879
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.
Cited by in corpus (6)
- Fast active learning for pure exploration in reinforcement learning
- Adaptive Reward-Free Exploration
- Adaptive Sampling for Best Policy Identification in Markov Decision Processes
- Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
- Gap-Dependent Unsupervised Exploration for Reinforcement Learning
- POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis