Convergence of discretization procedure in \(Q\)-learning

zbMATH Open0984.93023MaRDI QIDQ2725088

Cangpu Wu, Guofei Jiang, Huiqi Gao

Publication date: 21 April 2002

Published in: Control Theory \& Applications (Search for Journal in Brave)

zbMATH Keywords

discretizationdynamic programming\(Q\)-learning

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Design techniques (robust design, computer-aided design, etc.) (93B51) Numerical methods of relaxation type (49M20)

Recommendations

• The convergence of value iteration in discounted Markov decision processes 👍 👎
• Convergence results for single-step on-policy reinforcement-learning algorithms 👍 👎
• On the convergence of reinforcement learning 👍 👎
• Boundedness of iterates in \(Q\)-learning 👍 👎
• Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming 👍 👎
• Reinforcement learning via approximation of the Q-function 👍 👎
• Convergence of a Q-learning Variant for Continuous States and Actions 👍 👎
• Machine Learning: ECML 2004 👍 👎

This page was built for publication: Convergence of discretization procedure in \(Q\)-learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2725088)