"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 [NeuroEvolution of Augmenting Topologies] (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."
Defense Technical Information Center (DTIC): http://www.dtic.mil/dtic/
3rd International Conference on Agents and Artificial Intelligence, Rome, Italy, January 28-30, 2011