Biological arm motion through reinforcement learning

Authors:
Jun Izawa;Toshiyuki Kondo;Koji Ito
Affiliations:
Human and Information Science Laboratory, NTT Communication Science Laboratories 3-1, Sensory and Motor Research Group, Morinosato-Wakamiya, 243-01, Atsugi-shi, Japan;Interdisciplinary Graduate School Science and Engineering, Tokyo Institute of Technology, Department of Computational Intelligence and Systems Science, Morinosato-Wakamiya, 243-01, Yokohama, Japan;Interdisciplinary Graduate School Science and Engineering, Tokyo Institute of Technology, Department of Computational Intelligence and Systems Science, Morinosato-Wakamiya, 243-01, Yokohama, Japan
Venue:
Biological Cybernetics
Year:
2004

Citing 0
Cited 3

A reinforcement learning based neural network architecture for obstacle avoidance in multi-fingered grasp synthesis

Neurocomputing
Learning and generation of goal-directed arm reaching from scratch

Neural Networks
Combined Mechanisms of Internal Model Control and Impedance Control under Force Fields

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The present paper discusses an optimal learning control method using reinforcement learning for biological systems with a redundant actuator. It is difficult to apply reinforcement learning to biological control systems because of the redundancy in muscle activation space. We solve this problem with the following method. First, we divide the control input space into two subspaces according to a priority order of learning and restrict the search noise for reinforcement learning to the first priority subspace. Then the constraint is reduced as the learning progresses, with the search space extending to the second priority subspace. The higher priority subspace is designed so that the impedance of the arm can be high. A smooth reaching motion is obtained through reinforcement learning without any previous knowledge of the arm’s dynamics.