A unified NDP method for SMDP by an actor network

MaRDI QIDQ3513884zbMATH OpenFDO

Authors Hao Tang, D. Chen, Lei Zhou, Yuhua Wu

Publication date 6 August 2008

zbMATH Keywords

neuro-dynamic programmingperformance potentialssemi-Markov decision processesTD (\(\lambda\))learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Recommendations

• Unified NDP method based on TD(0) learning for both average and discounted Markov decision processes
• NDP methods for multi-chain MDPs
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• scientific article; zbMATH DE number 1786126
• scientific article; zbMATH DE number 1321699

Cited in

(2)

• NDP methods for multi-chain MDPs
• Unified NDP method based on TD(0) learning for both average and discounted Markov decision processes

This page was built for publication: A unified NDP method for SMDP by an actor network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3513884)