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


Personal Author(s) : Wright, Robert ; Loscalzo, Steven ; Yu, Lei


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a563362.pdf


Report Date : May 2012


Pagination or Media Count : 7


Abstract : Classical reinforcement learning techniques become impractical in domains with large complex state spaces. The size of a domain's 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.


Descriptors :   *LEARNING MACHINES , ALGORITHMS , AUTOMATION , ROBOTS , SIMULATION , SYMPOSIA


Subject Categories : Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE