Reinforcement learning based algorithms for average cost Markov decision processes

DOI10.1007/S10626-006-0003-YMaRDI QIDQ2643632zbMATH OpenOpenAlexFDO

Authors Mohammed Shahid Abdulla, Shalabh Bhatnagar

Publication date 27 August 2007

Published in Discrete Event Dynamic Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10626-006-0003-y

zbMATH Keywords

Markov decision processesreinforcement learningpolicy iterationsimultaneous perturbation stochastic approximationactor-critic algorithmsnormalized Hadamard matricesTD-learningtwo timescale stochastic approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Recommendations

• Learning algorithms for Markov decision processes with average cost
• Actor-critic algorithms with online feature adaptation
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Reinforcement learning for long-run average cost.
• Finite state approximation algorithms for average cost denumerable state Markov decision processes

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1786126 (Why is no real title available?)
• scientific article; zbMATH DE number 944076 (Why is no real title available?)
• A Simultaneous Perturbation Stochastic Approximation-Based Actor–Critic Algorithm for Markov Decision Processes
• A one-measurement form of simultaneous perturbation stochastic approximation
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Actor-critic algorithms for hierarchical Markov decision processes
• An analysis of temporal-difference learning with function approximation
• Asynchronous Stochastic Approximations
• Average cost temporal-difference learning
• Dynamic programming and stochastic control
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• OnActor-Critic Algorithms
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• The actor-critic algorithm as multi-time-scale stochastic approximation.

Cited in

(11)

• Learning algorithms for Markov decision processes with average cost
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Actor-critic algorithms for hierarchical Markov decision processes
• A constrained optimization perspective on actor-critic algorithms and application to network routing
• Learning algorithms for Markov decision processes
• Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm
• Reinforcement learning for long-run average cost.
• Natural actor-critic algorithms
• Multiscale Q-learning with linear function approximation
• Average cost temporal-difference learning
• Model-free average reward multi-step reinforcement learning

This page was built for publication: Reinforcement learning based algorithms for average cost Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2643632)