Selecting Near-Optimal Approximate State Representations in Reinforcement Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Selecting Near-Optimal Approximate State Representations in Reinforcement Learning

Abstract

We consider a reinforcement learning setting where the learner does not have explicit access to the states of the underlying Markov decision process (MDP). Instead, she has access to several models that map histories of past interactions to states. Here we improve over known regret bounds in this setting, and more importantly generalize to the case where the models given to the learner do not contain a true model resulting in an MDP representation but only approximations of it. We also give improved error bounds for state aggregation.
Not file

Dates and versions

hal-01057562 , version 1 (23-08-2014)

Identifiers

  • HAL Id : hal-01057562 , version 1

Cite

Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko. Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. International Conference on Algorithmic Learning Theory (ALT), Oct 2014, Bled, Slovenia. pp.140-154. ⟨hal-01057562⟩
164 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More