Selecting Near-Optimal Approximate State Representations in Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2014

Selecting Near-Optimal Approximate State Representations in Reinforcement Learning

Résumé

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.
Fichier non déposé

Dates et versions

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

Identifiants

  • HAL Id : hal-01057562 , version 1

Citer

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⟩
171 Consultations
0 Téléchargements

Partager

More