Undiscounted reinforcement learning algorithm based on performance potentials

zbMATH Open1123.68359MaRDI QIDQ5754334FDOQ5754334

Authors: Ruyi Zhou, Yang Gao 

Publication date: 22 August 2007

Recommendations

• From perturbation analysis to Markov decision processes and reinforcement learning
• Unified NDP method based on TD(0) learning for both average and discounted Markov decision processes
• scientific article; zbMATH DE number 2159039
• Algorithms for reinforcement learning.
• Performance optimization algorithms based on potentials for semi-Markov control processes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

This page was built for publication: Undiscounted reinforcement learning algorithm based on performance potentials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5754334)