Accession Number:

ADA563362

Title:

Embedded Incremental Feature Selection for Reinforcement Learning

Descriptive Note:

Conference paper

Corporate Author:

AIR FORCE RESEARCH LAB ROME NY INFORMATION DIRECTORATE

Report Date:

2012-05-01

Pagination or Media Count:

7.0

Abstract:

Classical reinforcement learning techniques become impractical in domains with large complex state spaces. The size of a domains state space is dominated by the number of features used to describe the state. Fortunately, in many real-world environments learning an effective policy does not usually require all the provided features. In this paper we present a feature selection algorithm for reinforcement learning called Incremental Feature Selection Embedded in NEAT IFSE-NEAT that incorporates sequential forward search into neuroevolutionary algorithm NEAT. We provide an empirical analysis on a realistic simulated domain with many irrelevant and relevant features. Our results demonstrate that IFSE-NEAT selects smaller and more effective feature sets than alternative approaches, NEAT and FS-NEAT, and superior performance characteristics as the number of available features increases.

Subject Categories:

  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE