19
115

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

Abstract

We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov decision process (MDP) for which an upper bound cc on the span of the optimal bias function is known. For an MDP with SS states, AA actions and ΓS\Gamma \leq S possible next states, we prove a regret bound of O~(cΓSAT)\widetilde{O}(c\sqrt{\Gamma SAT}), which significantly improves over existing algorithms (e.g., UCRL and PSRL), whose regret scales linearly with the MDP diameter DD. In fact, the optimal bias span is finite and often much smaller than DD (e.g., D=D=\infty in non-communicating MDPs). A similar result was originally derived by Bartlett and Tewari (2009) for REGAL.C, for which no tractable algorithm is available. In this paper, we relax the optimization problem at the core of REGAL.C, we carefully analyze its properties, and we provide the first computationally efficient algorithm to solve it. Finally, we report numerical simulations supporting our theoretical findings and showing how SCAL significantly outperforms UCRL in MDPs with large diameter and small span.

View on arXiv
Comments on this paper