arrow
返回

Implicit policy constraint for offline reinforcement learning

delete2024-03-15
delete0
delete
OA
AI
Z
Zhiyong Peng
Y
Yadong Liu
Z
Zongtan Zhou *
DOI:10.1049/cit2.12304delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Offline reinforcement learning (RL) aims to learn policies entirely from passively collected datasets, making it a data-driven decision method. One of the main challenges in offline RL is the distribution shift problem, which causes the algorithm to visit out-of-distribution (OOD) samples. The distribution shift can be mitigated by constraining the divergence between the target policy and the behaviour policy. However, this method can overly constrain the target policy and impair the algorithm's performance, as it does not directly distinguish between in-distribution and OOD samples. In addition, it is difficult to learn and represent multi-modal behaviour policy when the datasets are collected by several different behaviour policies. To overcome these drawbacks, the authors address the distribution shift problem by implicit policy constraints with energy-based models (EBMs) rather than explicitly modelling the behaviour policy. The EBM is powerful for representing complex multi-modal distributions as well as the ability to distinguish in-distribution samples and OODs. Experimental results show that their method significantly outperforms the explicit policy constraint method and other baselines. In addition, the learnt energy model can be used to indicate OOD visits and alert the possible failure.
Keyword:
artificial intelligence
artificial neural network
learning (artificial intelligence)
planning (artificial intelligence)

期刊

CAAI Transactions on Intelligence Technology 封面图
CAAI Transactions on Intelligence Technology
IF:
7.3
论文数:
671
被引数:
2.4K

机构

N
national university of defense technology - china
学者数:
1.8W
论文数: 1.4W
被引数: 9
引用论文

引用论文

Learning agile and dynamic motor skills for legged robots
err2019-01-30
err795
errOAAI
errHwangbo, Jemin; Lee, Joonho; Dosovitskiy, Alexey; Bellicoso, Dario; Tsounis, Vassilios; Koltun, Vladlen; Hutter, Marco
err分享
err收藏
Learning dexterous in-hand manipulation学习灵巧的手操作
err2019-11-18
err818
errOAAI
errAndrychowicz, Marcin; Baker, Bowen; Chociej, Maciek; Jozefowicz, Rafal; McGrew, Bob; Pachocki, Jakub; Petron, Arthur; Plappert, Matthias; Powell, Glenn; Ray, Alex; Schneider, Jonas; Sidor, Szymon; Tobin, Josh; Welinder, Peter; Weng, Lilian; Zaremba, Wojciech
err分享
err收藏
Conservative network for offline reinforcement learning
err2023-12-01
err0
PREAI
errPeng, Zhiyong; Liu, Yadong; Chen, Haoqiang; Zhou, Zongtan
err分享
err收藏
没有更多内容