Q-Learning in Continuous State and Action Spaces

Authors:
Chris Gaskett;David Wettergreen;Alexander Zelinsky
Affiliations:
-;-;-
Venue:
AI '99 Proceedings of the 12th Australian Joint Conference on Artificial Intelligence: Advanced Topics in Artificial Intelligence
Year:
1999

Citing 4
Cited 10

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching

Machine Learning
Experiments with reinforcement learning in problems with continuous state and action spaces

Adaptive Behavior
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning

A Quadratic Programming Formulation of a Moving Ball Interception and Shooting Behaviour, and Its Application to Neural Network Control

RoboCup 2000: Robot Soccer World Cup IV
A Two-Stage Relational Reinforcement Learning with Continuous Actions for Real Service Robots

MICAI '09 Proceedings of the 8th Mexican International Conference on Artificial Intelligence
Reinforcement learning using Voronoi space division

Artificial Life and Robotics
Exploring continuous action spaces with diffusion trees for reinforcement learning

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Continuous state/action reinforcement learning: A growing self-organizing map approach

Neurocomputing
The implementation of Q-learning for problems in continuous state and action space using SOM-based fuzzy systems

ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
A dynamic route change mechanism for mobile ad hoc networks

International Journal of Communication Networks and Distributed Systems
Applying neural network to reinforcement learning in continuous spaces

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Task-Driven discretization of the joint space of visual percepts and continuous actions

ECML'06 Proceedings of the 17th European conference on Machine Learning
Learning to approach a moving ball with a simulated two-wheeled robot

RoboCup 2005

Quantified Score

Hi-index	0.00

Visualization

Abstract

Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Q- learning is commonly applied to problems with discrete states and actions. We describe a method suitable for control tasks which require continuous actions, in response to continuous states. The system consists of a neureil network coupled with a novel interpolator. Simulation results are presented for a non-holonomic control task. Advantage Learning, a variation of Q-learning, is shown enhance learning speed and reliability for this task.