Feature discovery in reinforcement learning using genetic programming - Archive ouverte HAL Access content directly
Conference Papers Year : 2008

Feature discovery in reinforcement learning using genetic programming

(1) , (1, 2, 3)
1
2
3

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-00826056 , version 1

Cite

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⟩
149 View
216 Download

Share

Gmail Facebook Twitter LinkedIn More