Q-learning algorithms with random truncation bounds and applications to effective parallel computing

DOI10.1007/S10957-007-9331-9MaRDI QIDQ946195zbMATH OpenOpenAlexFDO

Authors Le Yi Wang, G. Yin, Cheng-Zhong Xu

Publication date 22 September 2008

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10957-007-9331-9

zbMATH Keywords

rate of convergenceconvergenceQ-learningrecursive algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05) Parallel algorithms in computer science (68W10)

Recommendations

• Asynchronous stochastic approximation and Q-learning
• A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm
• Boundedness of iterates in \(Q\)-learning
• Exploiting the structural properties of the underlying Markov decision problem in the Q-learning algorithm
• New algorithms of the Q-learning type

Cites work

• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• scientific article; zbMATH DE number 3992716 (Why is no real title available?)
• scientific article; zbMATH DE number 967422 (Why is no real title available?)
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• Asymptotic properties of sign algorithms for adaptive filtering
• Asynchronous stochastic approximation and Q-learning
• On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm
• Stochastic approximation algorithms for parallel and distributed processing
• Stochastic approximation and its applications
• Stochastic approximation: Theory and applications
• \({\mathcal Q}\)-learning

Cited in

(4)

• A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm
• Two-time scale reinforcement learning and applications to production planning
• Asynchronous stochastic approximation and Q-learning
• PQN and DQN: algorithms for expression microarrays

This page was built for publication: Q-learning algorithms with random truncation bounds and applications to effective parallel computing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q946195)