An online actor-critic algorithm with function approximation for constrained Markov decision processes

DOI10.1007/S10957-012-9989-5MaRDI QIDQ438776zbMATHOpenAlexFDO

Authors Shalabh Bhatnagar, K. Lakshmanan

Publication date 31 July 2012

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

Full work available at URL https://doi.org/10.1007/s10957-012-9989-5

zbMATH Keywords

function approximationactor critic algorithmconstrained Markov decision processlong-run average cost criterion

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Markov and semi-Markov decision processes (90C40)

Recommendations

• An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes
• An actor-critic algorithm for constrained Markov decision processes
• A constrained optimization perspective on actor-critic algorithms and application to network routing
• Actor-critic algorithms with online feature adaptation
• Learning algorithms for finite horizon constrained Markov decision processes

Cites work

• scientific article; zbMATH DE number 5348356 (Why is no real title available?)
• scientific article; zbMATH DE number 48727 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 1348599 (Why is no real title available?)
• scientific article; zbMATH DE number 941166 (Why is no real title available?)
• An actor-critic algorithm for constrained Markov decision processes
• An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes
• Asynchronous Stochastic Approximations
• Average cost temporal-difference learning
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Natural actor-critic algorithms
• OnActor-Critic Algorithms
• Optimal flow control of a class of queueing networks in equilibrium
• Perturbation theory and finite Markov chains
• Simulation-based optimization of Markov reward processes
• The Borkar-Meyn theorem for asynchronous stochastic approximations
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning

Cited in

(15)

• Suboptimal control for nonlinear systems with disturbance via integral sliding mode control and policy iteration
• Queueing network controls via deep reinforcement learning
• Event-based optimization approach for solving stochastic decision problems with probabilistic constraint
• Actor-critic algorithms with online feature adaptation
• A constrained optimization perspective on actor-critic algorithms and application to network routing
• An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes
• Optimal deterministic controller synthesis from steady-state distributions
• Learning algorithms for discounted MDPs with constraints
• Learning algorithms for finite horizon constrained Markov decision processes
• Multiscale Q-learning with linear function approximation
• An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
• On the sample complexity of actor-critic method for reinforcement learning with function approximation
• Variance-constrained actor-critic algorithms for discounted and average reward MDPs
• Risk-constrained reinforcement learning with percentile risk criteria
• An actor-critic algorithm for constrained Markov decision processes

This page was built for publication: An online actor-critic algorithm with function approximation for constrained Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q438776)