Feature discovery in reinforcement learning using genetic programming

Sertan Girgin 1 Philippe Preux 1, 2, 3
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
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.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-00826056
Contributor : Preux Philippe <>
Submitted on : Wednesday, June 5, 2013 - 8:49:53 AM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Friday, September 6, 2013 - 4:08:29 AM

File

fdrl.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00826056, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

386

Files downloads

268