Learning Exploration Strategies in Model-Based Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Learning Exploration Strategies in Model-Based Reinforcement Learning

Résumé

Reinforcement learning (RL) is a paradigm for learning sequential decision making tasks. However, typically the user must hand-tune exploration parameters for each different domain and/or algorithm that they are using. In this work, we present an algorithm called leo for learning these exploration strategies on-line. This algorithm makes use of bandit-type algorithms to adaptively select exploration strategies based on the rewards received when following them. We show empirically that this method performs well across a set of five domains. In contrast, for a given algorithm, no set of parameters is best across all domains. Our results demonstrate that the leo algorithm successfully learns the best exploration strategies on-line, increasing the received reward over static parameterizations of exploration and reducing the need for hand-tuning exploration parameters.
Fichier non déposé

Dates et versions

hal-00871861 , version 1 (10-10-2013)

Identifiants

  • HAL Id : hal-00871861 , version 1

Citer

Todd Hester, Peter Stone, Manuel Lopes. Learning Exploration Strategies in Model-Based Reinforcement Learning. AAMAS 2013 - 12th International Conference on Autonomous Agents and Multiagent Systems, May 2013, St. Paul, MN, United States. pp.1069-1076. ⟨hal-00871861⟩
164 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More