Learning Exploration Strategies in Model-Based Reinforcement Learning

Todd Hester; Peter Stone; Manuel Lopes

Conference papers

Learning Exploration Strategies in Model-Based Reinforcement Learning

Todd Hester ¹ Peter Stone ¹ Manuel Lopes ²

1 CS - Departement of Computer Science [Austin]

2 Flowers - Flowing Epigenetic Robots and Systems

Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes

Abstract : 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.

Document type :

Conference papers

Domain :

Computer Science [cs] / Machine Learning [cs.LG]

Complete list of metadata

https://hal.inria.fr/hal-00871861
Contributor : Manuel Lopes Connect in order to contact the contributor
Submitted on : Thursday, October 10, 2013 - 5:38:29 PM
Last modification on : Friday, December 3, 2021 - 11:34:06 AM

Learning Exploration Strategies in Model-Based Reinforcement Learning

Identifiers

Collections

Citation

Export

Metrics

Contact Legal Notice Personal Data

Learning Exploration Strategies in Model-Based Reinforcement Learning

Identifiers

Collections

Citation

Export

Share

Metrics

Contact Legal Notice Personal Data