The Borkar-Meyn theorem for asynchronous stochastic approximations

DOI10.1016/j.sysconle.2011.04.002zbMath1222.93229MaRDI QIDQ553371

Shalabh Bhatnagar

Publication date: 27 July 2011

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.sysconle.2011.04.002

zbMATH Keywords

temporal difference learning; asynchronous stochastic approximation with delays; the Borkar-Meyn theorem

Mathematics Subject Classification ID

93E15: Stochastic stability in control theory

93E35: Stochastic learning and adaptive control

Related Items

An online actor-critic algorithm with function approximation for constrained Markov decision processes, Q-learning for Markov decision processes with a satisfiability criterion, Whittle index based Q-learning for restless bandits with average reward, Event-driven stochastic approximation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes
• Natural actor-critic algorithms
• An analysis of temporal-difference learning with function approximation
• Asynchronous Stochastic Approximations
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning