Reinforcement learning with via-point representation

Authors:
Hiroyuki Miyamoto;Jun Morimoto;Kenji Doya;Mitsuo Kawato
Affiliations:
Kawato Dynamic Brain Project, Japan Science and Technology Corporation, Kyoto, Japan and Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Hibikino 2-4, Waka ...;ATR Computational Neuroscience Laboratories, Kyoto, Japan;ATR Computational Neuroscience Laboratories, Kyoto, Japan;ATR Computational Neuroscience Laboratories, Kyoto, Japan
Venue:
Neural Networks
Year:
2004

Citing 8
Cited 6

A neural network model for arm trajectory formation using forward and inverse dynamics models

Neural Networks
Optimization and learning in neural networks for formation and control of coordinated movement

Attention and performance XIV (silver jubilee volume)
A Kendama learning robot based on bi-directional theory

Neural Networks - 1996 Special issue: four major hypotheses in neuroscience
A tennis serve and upswing learning robot based on bi-directional theory

Neural Networks - Special issue on neural control and robotics: biology and technology
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Robot Learning From Demonstration

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Roles of Macro-actions in Accelerating Reinforcement Learning TITLE2:

Roles of Macro-actions in Accelerating Reinforcement Learning TITLE2:
Reinforcement Learning in Continuous Time and Space

Neural Computation

Neural network control of an inverted pendulum on a cart

ROCOM'09 Proceedings of the 9th WSEAS international conference on Robotics, control and manufacturing technology
Constructing action set from basis functions for reinforcement learning of robot control

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Planning-space shift learning: variable-space motion planning toward flexible extension of body schema

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Planning-Space Shift Motion Generation: Variable-space Motion Planning Toward Flexible Extension of Body Schema

Journal of Intelligent and Robotic Systems
Application of neural networks for control of inverted pendulum

WSEAS Transactions on Circuits and Systems
DCOB: Action space for reinforcement learning of high DoF robots

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a new learning framework for motor control. This framework consists of two components: reinforcement learning and via-point representation. In the field of motor control, conventional reinforcement learning has been used to acquire control sequences such as cart-pole or stand-up robot control. Recently, researchers have become interested in hierarchical architecture, such as multiple levels, and multiple temporal and spatial scales. Our new framework contains two levels of hierarchical architecture. The higher level is implemented using via-point representation, which corresponds to macro-actions or multiple time scales. The lower level is implemented using a trajectory generator that produces primitive actions. Our framework can modify the ongoing movement by means of temporally localized via-points and trajectory generation. Successful results are obtained in computer simulation of the cart-pole swing up task.