Autonomous reinforcement learning with experience replay

This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor-critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. (c) 2012 Elsevier Ltd. All rights reserved.


Published in:
Neural Networks, 41, 156-167
Year:
2013
Publisher:
Oxford, Pergamon-Elsevier Science Ltd
ISSN:
0893-6080
Keywords:
Note:
Special Issue on Autonomous Learning
Laboratories:




 Record created 2013-10-01, last modified 2018-03-18

External link:
Download fulltext
URL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)