Undiscounted reinforcement learning algorithm based on performance potentials

MaRDI QIDQ5754334zbMATH OpenFDO

Authors Ruyi Zhou, Yang Gao

Publication date 22 August 2007

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

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

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)