Acquiring Body Representation for Reinforcement Learning Based on Slow Feature Analysis

The center of spatio-temporal representation for own body and its surrounding space is supposed at the parietal cortex in human brains, but the mechanism how the brain computes them is still not clearly understood though its hierarchical representation is expected. One of such hierarchical models, this paper propose a method which integrates multimodal information based on the Slow Feature Analysis (SFA) that enables sensory data abstraction in one modality and integration of abstracted multi-modal sensory information. To verify the proposed method, the reinforcement learning of reaching behavior is applied where the acquired representation from the visual and somatosensory information of arm movements of a robot is utilised as state space representation. The simulation result shows that multimodal information related to self movement is transformed into lower dimensional data that changes slowly, which is useful for reinforcement learning to improve its performance. Keywords—Slow Feature Analysis, Multimodal, Body Representation, Reinforcement Learning