Feature discovery in reinforcement learning using genetic programming - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Feature discovery in reinforcement learning using genetic programming

Résumé

The goal of reinforcement learning is to find a policy, directly or indirectly through a value function, that maximizes the expected re- ward accumulated by an agent over time based on its interactions with the environment; a function of the state has to be learned. In some prob- lems, it may not be feasible, or even possible, to use the state variables as they are. Instead, a set of features are computed and used as in- put. However, finding a "good" set of features is generally a tedious task which requires a good domain knowledge. In this paper, we propose a ge- netic programming based approach for feature discovery in reinforcement learning. A population of individuals each representing possibly different number of candidate features is evolved, and feature sets are evaluated by their average performance on short learning trials. The results of ex- periments conducted on several benchmark problems demonstrate that the resulting features allow the agent to learn better policies.
Fichier principal
Vignette du fichier
fdrl.pdf (154.1 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00826056 , version 1 (05-06-2013)

Identifiants

  • HAL Id : hal-00826056 , version 1

Citer

Sertan Girgin, Philippe Preux. Feature discovery in reinforcement learning using genetic programming. 11th European Conference on Genetic Programming (EUROGP), 2008, Naples, Italy. pp.218-229. ⟨hal-00826056⟩
162 Consultations
268 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More