An Information-Theoretic On-Line Update Principle for Perception-Action Coupling

back to our research

An Information-Theoretic On-Line Update Principle for Perception-Action Coupling

24-28 September 2017, Vancouver, Canada

(not yet available online)

IEEE/RSJ International Conference on Intelligent Robots and Systems, Vancouver, Canada, Sep 24-28, 2017

Authors: Zhen Peng, Tim Genewein, Felix Leibfried (PROWLER.io), and Daniel Braun

Abstract: Inspired by findings of sensorimotor coupling in humans and animals, there has recently been a growing interest in the interaction between action and perception in robotic systems. Here we consider perception and action as two serial information channels with limited information-processing capacity. We follow and formulate a constrained optimization problem that maximizes utility under limited information-processing capacity in the two channels. As a solution, we obtain an optimal perceptual channel and an optimal action channel that are coupled such that perceptual information is optimized with respect to downstream processing in the action module. The main novelty of this study is that we propose an online optimization procedure to find bounded-optimal perception and action channels in parameterized serial perception-action systems. In particular, we implement the perceptual channel as a multi-layer neural network and the action channel as a multinomial distribution. We illustrate our method in a NAO robot simulator with a simplified cup lifting task.

Bounded-Rationality

Information Theory

Reinforcement Learning


See paper