Better Sampling Strategy for Locomotion Control Tasks

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)

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  -