返回
Implicit policy constraint for offline reinforcement learning
DOI:10.1049/cit2.12304.png)
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
IF:
7.3
论文数:
671
被引数:
2.4K
机构
引用论文
Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
Fabrication of porous hollow γ-Al2O3 nanofibers by facile electrospinning and its application for water remediation静电纺丝法制备多孔中空 γ-Al2O3纳米纤维及其在水体修复中的应用
ICT for informal workers in Sub-Saharan Africa: Systematic review and analysis撒哈拉以南非洲非正规工人的信通技术: 系统回顾和分析
没有更多内容

