Robot reinforcement learning accuracy-based learning classifier systems with Fuzzy Policy Gradient descent(XCS-FPGRL)

DOI

10.2991/ameii-15.2015.187How to use a DOI?

Keywords

Convergence; Rrobot; Reinforcement learning; Accuracy-based learning classifier system with Gradient descent (XCS-FPGRL);XCS Accuracy-based learning classifier system

Abstract

This paper presented a novel approach XCS-FPGRL to research on robot reinforcement learning. XCS-FPGRL combines covering operator and genetic algorithm. The systems is responsible for adjusting precision and reducing search space according to some reward obtained from the environment, acts as an innovation discovery component which is responsible for discovering new better reinforcement learning rules. The experiment and simulation showed that robot reinforcement learning can achieved convergence very quickly.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jie Shao
AU  - Jingru Yu
PY  - 2015/04
DA  - 2015/04
TI  - Robot reinforcement learning accuracy-based learning classifier systems with Fuzzy Policy Gradient descent(XCS-FPGRL)
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 1013
EP  - 1018
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.187
DO  - 10.2991/ameii-15.2015.187
ID  - Shao2015/04
ER  -