Free-Energy Based Reinforcement Learning for Vision-Based Navigation with High-Dimensional Sensory Inputs

Abstract

Free-energy based reinforcement learning was proposed for learning in high-dimensional state and action spaces, which cannot be handled by standard function approximation methods in reinforcement learning. In the free-energy reinforcement learning method, the action-value function is approximated as the negative free energy of a restricted Boltzmann machine. In this paper, we test if it is feasible to use free-energy reinforcement learning for real robot control with raw, high-dimensional sensory inputs through the extraction of task-relevant features in the hidden layer. We first demonstrate, in simulation, that a small mobile robot could efficiently learn a vision-based navigation and battery capturing task. We then demonstrate, for a simpler battery capturing task, that free-energy reinforcement learning can be used for on-line learning in a real robot. The analysis of learned weights showed that action-oriented state coding was achieved in the hidden layer.