A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning

DOI10.1016/J.INS.2023.119011MaRDI QIDQ6121659

Xinyang Deng, Yixin He, Wen Jiang, Fanghui Huang

Publication date: 26 March 2024

Published in: Information Sciences (Search for Journal in Brave)

zbMATH Keywords

reinforcement learningaction confidence limitdeep auto-encoder networkexploration policyuncertainty of action

Mathematics Subject Classification ID

Nonparametric tolerance and confidence regions (62G15) Learning and adaptive systems in artificial intelligence (68T05) Source coding (94A29)

Cites Work

• Unnamed Item
• \({\mathcal Q}\)-learning
• Exploration of multi-state environments: Local measures and back-propagation of uncertainty
• An online-learning-based evolutionary many-objective algorithm
• AnD: a many-objective evolutionary algorithm with angle-based selection and shift-based density estimation
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• An adaptive polyploid memetic algorithm for scheduling trucks at a cross-docking terminal

This page was built for publication: A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning