Reinforcement learning algorithm with CTRNN in continuous action space

Authors:
Hiroaki Arie;Jun Namikawa;Tetsuya Ogata;Jun Tani;Shigeki Sugano
Affiliations:
Department of Mechanical Engineering, Waseda University, Tokyo, Japan;RIKEN, Brain Science Institute, Laboratory for Behavior and Dynamic Cognition, Saitama, Japan;Graduate School of Infomatics, Kyoto University, Kyoto, Japan;RIKEN, Brain Science Institute, Laboratory for Behavior and Dynamic Cognition, Saitama, Japan;Department of Mechanical Engineering, Waseda University, Tokyo, Japan
Venue:
ICONIP'06 Proceedings of the 13 international conference on Neural Information Processing - Volume Part I
Year:
2006

Citing 6
Cited 2

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Reinforcement learning with hidden states

Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Learning to Predict by the Methods of Temporal Differences

Machine Learning
Reinforcement learning with selective perception and hidden state

Reinforcement learning with selective perception and hidden state
Reinforcement Learning in Continuous Time and Space

Neural Computation
Model-based learning for mobile robot navigation from the dynamicalsystems perspective

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Acquiring Rules for Rules: Neuro-Dynamical Systems Account for Meta-Cognition

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Reinforcement learning of multiple tasks using parametric bias

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

There are some difficulties in applying traditional reinforcement learning algorithms to motion control tasks of robot. Because most algorithms are concerned with discrete actions and based on the assumption of complete observability of the state. This paper deals with these two problems by combining the reinforcement learning algorithm and CTRNN learning algorithm. We carried out an experiment on the pendulum swing-up task without rotational speed information. It is shown that the information about the rotational speed, which is considered as a hidden state, is estimated and encoded on the activation of a context neuron. As a result, this task is accomplished in several hundred trials using the proposed algorithm.