[en] We derive an algorithm for selecting from the set of samples gathered by a reinforcement learning agent interacting with a deterministic environment, a concise set from which the agent can extract a good policy.
The reinforcement learning agent is assumed to extract policies from sets of samples by solving a sequence of standard supervised learning regression problems. To identify concise sets, we adopt a criterion based on an error function defined from the sequence of models produced by the supervised learning algorithm.
We evaluate our approach on two-dimensional maze problems and show its good performances when problems are continuous.
Disciplines :
Computer science
Author, co-author :
Ernst, Damien ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Selecting concise sets of samples for a reinforcement learning agent
Publication date :
2005
Event name :
3rd International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS 2005)
Event place :
Singapore, Singapore
Event date :
22-26 August 2005
Audience :
International
Main work title :
Proceedings of the 3rd International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS 2005)
