A reinforcement learning algorithm based on information entropy

MaRDI QIDQ3071423zbMATH OpenFDO

Authors Yun Zhao, Weili Hu, Qingwei Chen

Publication date 5 February 2011

zbMATH Keywords

reinforcement learninginformation entropyaction-selection

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Measures of information, entropy (94A17)

Recommendations

• Reinforcement learning theory, algorithms and its application
• Maximum entropy-based optimal threshold selection using deterministic reinforcement learning with controlled randomization
• Algorithm of stable state spaces in reinforcement learning
• Uncertainty Propagation for Efficient Exploration in Reinforcement Learning
• A reinforcement learning algorithm based on model

Cited in

(3)

• A reinforcement learning algorithm based on model
• scientific article; zbMATH DE number 1728681 (Why is no real title available?)
• Theory and Applications of Models of Computation

This page was built for publication: A reinforcement learning algorithm based on information entropy

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3071423)