Work

Fast Feature Selection for Linear Value Function Approximation

Year: 2021

Type: conference-paper

Abstract: Linear value function approximation is a standard approach to solving reinforcement learning problems with large state spaces. Since designing good approximation features is difficult, automatic feature selection is an important research topic. We propose a new method for feature selection that is based on a low-rank factorization of the transition matrix. Our approach derives features directly from high-dimensional raw inputs, such as image data. The method is easy to implement using SVD, and our experiments show that it is faster and more stable than alternative methods.

Source: Proceedings of the International Conference on Automated Planning and Scheduling

DOI: 10.1609/icaps.v29i1.3527

Authors: Bahram Behzadian, Soheil Gharatappeh, Marek Petrik

Institution: University of New Hampshire

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: National Science Foundation

Award: III: Small: Robust Reinforcement Learning for Invasive Species Management