Basis Function Construction in Reinforcement Learning using Cascade-Correlation Learning Architecture

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 : In reinforcement learning, it is a common practice to map the state(-action) space to a different one using ba- sis 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 func- tions 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 ap- proach can be applied to Least Squares Policy Iteration al- gorithm 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-00826054
Contributor : Preux Philippe <>
Submitted on : Monday, May 27, 2013 - 3:39:03 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Tuesday, September 3, 2013 - 9:41:48 AM

File

icmla08.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00826054, version 1

Collections

Citation

Sertan Girgin, Philippe Preux. Basis Function Construction in Reinforcement Learning using Cascade-Correlation Learning Architecture. International Conference on Machine Learning and Applications, Dec 2008, San Diego, United States. pp.75-82. ⟨hal-00826054⟩

Share

Metrics

Record views

401

Files downloads

483