Accession Number:

ADA619305

Title:

Predictive Feature Selection for Genetic Policy Search

Descriptive Note:

Journal article

Corporate Author:

AIR FORCE RESEARCH LAB ROME NY INFORMATION DIRECTORATE

Report Date:

2014-05-22

Pagination or Media Count:

35.0

Abstract:

Automatic learning of control policies is becoming increasingly important to allow autonomous agents to operate alongside, or in place of, humans in dangerous and fast - paced situations. Reinforcement learning RL, including genetic policy search algorithms, comprise a promising technology area capable of learning such control policies. Unfortunately, RL techniques can take prohibitively long to learn a sufficiently good control policy in environments described by many sensors features. We argue that in many cases only a subset of available features are needed to learn the task at hand, since others may represent irrelevant or redundant information. In this work, we propose a predictive feature selection framework that analyzes data obtained during execution of a genetic policy search algorithm to identify relevant features on - line. This serves to constrain the policy search space and reduces the time needed to locate a sufficiently good policy by embedding feature selection into the process of learning a control policy. We explore this framework through an instantiation called predictive feature selection embedded in neuroevolution of augmenting topology NEAT, or P FS - NEAT. In an empirical study, we demonstrate that PFS - NEAT is capable of enabling NEAT to successfully find good control policies in two benchmark environments, and show that it can outperform three competing feature selection algorithms, FS - NEAT, FD - NEA T, and SAFS - NEAT, in several variants of these environments.

Subject Categories:

  • Statistics and Probability
  • Computer Programming and Software
  • Cybernetics
  • Human Factors Engineering and Man Machine Systems

Distribution Statement:

APPROVED FOR PUBLIC RELEASE