DeLTA Seminar by Hippolyte Raymond Bourel
Speaker
Hippolyte Raymond Bourel
Title
Model-Based Reinforcement Learning Exploiting State-Action Equivalence
Abstract
Leveraging an equivalence property in the state-space of a Markov Decision Process (MDP) has been investigated in several studies. This paper studies equivalence structure in the reinforcement learning (RL) setup, where transition distributions are no longer assumed to be known. We present a notion of similarity between transition probabilities of various state-action pairs of an MDP, which naturally defines an equivalence structure in the state-action space. We present equivalence-aware confidence sets for the case where the learner knows the underlying structure in advance. These sets are provably smaller than their corresponding equivalence-oblivious counterparts. In the more challenging case of an unknown equivalence structure, we present an algorithm called ApproxEquivalence that seeks to find an (approximate) equivalence structure, and define confidence sets using the approximate equivalence. To illustrate the efficacy of the presented confidence sets, we present C-UCRL, as a natural modification of UCRL2 for RL in undiscounted MDPs. In the case of a known equivalence structure, we show that C-UCRL improves over UCRL2 in terms of regret by a factor of sqrt(SA/C), in any communicating MDP with S states, A actions, and C classes, which corresponds to a massive improvement when C ≪ SA. To the best of our knowledge, this is the first work providing regret bounds for RL when an equivalence structure in the MDP is efficiently exploited. In the case of an unknown equivalence structure, we show through numerical experiments that C-UCRL combined with ApproxEquivalence outperforms UCRL2 in ergodic MDPs.
Joint work with Mahsa Asadi, Mohammad Sadegh Talebi, and Odalric Maillard
http://www.acml-conf.org/2019/conference/accepted-papers/116/
-------------------
You can subscribe to DeLTA Seminar mailing list by sending an empty email to delta-seminar-join@list.ku.dk.
Information about DeLTA Seminars is available at the DeLTA Lab page.
DeLTA is a research group affiliated with the Department of Computer Science at the University of Copenhagen studying diverse aspects of Machine Learning Theory and its applications, including, but not limited to Reinforcement Learning, Online Learning and Bandits, PAC-Bayesian analysis