Predictive Feature Selection for Genetic Policy Search

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 22, 2014
Accession Number
ADA619305

Entities

People

  • Lei Yu
  • Robert Wright
  • Steven Loscalzo

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Autonomous Agents
  • Bayesian Networks
  • Computational Science
  • Computer Science
  • Dimensionality Reduction
  • Feature Selection
  • Genetic Variation
  • Information Science
  • Machine Learning
  • Mesh Networks
  • Network Science
  • Probability
  • Reinforcement Learning
  • Supervised Machine Learning
  • Topology

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Economics
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Biotechnology
  • Space