Conservative network for offline reinforcement learning

Zhiyong Peng; Yadong Liu; Haoqiang Chen; Zongtan Zhou

doi:10.1016/j.knosys.2023.111101

ScienceGate Book Chapters

JOURNAL ARTICLE

Conservative network for offline reinforcement learning

Zhiyong Peng Yadong Liu Haoqiang Chen Zongtan Zhou

Year: 2023 Journal: Knowledge-Based Systems Vol: 282 Pages: 111101-111101 Publisher: Elsevier BV

DOI: 10.1016/j.knosys.2023.111101

Get Full-Text PDF Get Analytical Report

Keywords:

Reinforcement learning Computer science Hyperparameter Offline learning Simplicity Function (biology) Artificial intelligence Network architecture Machine learning Simple (philosophy) Property (philosophy) Artificial neural network Architecture Value (mathematics) Task (project management) Engineering Online learning

Metrics

Cited By

1.53

FWCI (Field Weighted Citation Impact)

Refs

0.82

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Reinforcement Learning in Robotics

Physical Sciences → Computer Science → Artificial Intelligence

Adaptive Dynamic Programming Control

Physical Sciences → Computer Science → Computational Theory and Mathematics

Adversarial Robustness in Machine Learning

Physical Sciences → Computer Science → Artificial Intelligence

Conservative network for offline reinforcement learning

Metrics

Citation History

Topics

Related Documents

Stable Conservative Q-Learning for Offline Reinforcement Learning

Adaptable Conservative Q-Learning for Offline Reinforcement Learning

Conservative In-Distribution Q-Learning for Offline Reinforcement Learning

Offline Quantum Reinforcement Learning in a Conservative Manner

DOMAIN: Mildly Conservative Model-Based Offline Reinforcement Learning