Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

Better Sampling Strategy for Locomotion Control Tasks

Authors
Junning Huang, Zhifeng Hao
Corresponding Author
Junning Huang
Available Online May 2018.
DOI
10.2991/ncce-18.2018.135How to use a DOI?
Keywords
TRPO; OU; high dimensional; control tasks; sampling strategy; performance; convergence.
Abstract

Recently, model-free reinforcement learning algorithms such as TRPO for solving locomotion control tasks has achieved great success. But for difficult locomotion problem with high dimensional visual observation, these algorithms are not sample efficient. This paper proposes an OU process sampling strategy for locomotion control tasks. As experimental results show, TRPO algorithm with OU process sampling strategy shows better performance and better convergence compare with TRPO without OU process strategy.

Copyright
© 2018, 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)

Volume Title
Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
Series
Advances in Intelligent Systems Research
Publication Date
May 2018
ISBN
10.2991/ncce-18.2018.135
ISSN
1951-6851
DOI
10.2991/ncce-18.2018.135How to use a DOI?
Copyright
© 2018, 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/).

Cite this article

TY  - CONF
AU  - Junning Huang
AU  - Zhifeng Hao
PY  - 2018/05
DA  - 2018/05
TI  - Better Sampling Strategy for Locomotion Control Tasks
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 819
EP  - 824
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.135
DO  - 10.2991/ncce-18.2018.135
ID  - Huang2018/05
ER  -