Incremental Basis Function Expansion in Reinforcement Learning using Cascade-Correlation Networks

Sertan Girgin 1 Philippe Preux 1, 2
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : In reinforcement learning, it is a common practice to map the state(-action) space to a different one using basis functions. This transformation aims to represent the input data in a more informative form that facilitates and improves subsequent steps. As a ''good'' set of basis functions result in better solutions and defining such functions becomes a challenge with increasing problem complexity, it is beneficial to be able to generate them automatically. In this paper, we propose a new approach based on Bellman residual for constructing basis functions using cascade-correlation learning architecture. We show how this approach can be applied to Least Squares Policy Iteration algorithm in order to obtain a better approximation of the value function, and consequently improve the performance of the resulting policies. We also present the effectiveness of the method empirically on some benchmark problems.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00356262
Contributor : Preux Philippe <>
Submitted on : Thursday, November 8, 2012 - 3:33:10 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Saturday, February 9, 2013 - 2:25:10 AM

File

icmla08.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00356262, version 1

Collections

Citation

Sertan Girgin, Philippe Preux. Incremental Basis Function Expansion in Reinforcement Learning using Cascade-Correlation Networks. 8th International Conference on Machine Learning and Applications, Dec 2008, San Diego, United States. pp.75-82. ⟨inria-00356262⟩

Share

Metrics

Record views

500

Files downloads

435