Accelerating the convergence of value iteration by using partial transition functions

DOI10.1016/J.EJOR.2013.02.029MaRDI QIDQ2355825zbMATH OpenOpenAlexFDO

Authors E. F. Arruda, Fabrício O. Ourique, Anthony Almudevar, Jason LaCombe

Publication date 28 July 2015

Published in European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ejor.2013.02.029

zbMATH Keywords

optimizationdynamic programmingMarkov processes

Mathematics Subject Classification ID

Queues and service in operations research (90B22) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• An empirical study of policy convergence in Markov decision process value iteration
• Accelerated modified policy iteration algorithms for Markov decision processes
• Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes
• Factored value iteration converges
• The convergence of value iteration in discounted Markov decision processes

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• An optimal one-way multigrid algorithm for discrete-time stochastic control
• Approximate Dynamic Programming
• Approximate Fixed Point Iteration with an Application to Infinite Horizon Markov Decision Processes
• Approximate dynamic programming via direct search in the space of value function approximations
• Dynamic multi-appointment patient scheduling for radiation therapy
• LAO*: A heuristic search algorithm that finds solutions with loops
• Optimal Approximation Schedules for a Class of Iterative Algorithms, With an Application to Multigrid Value Iteration
• Optimization of a special case of continuous-time Markov decision processes with compact action set
• Prioritization methods for accelerating MDP solvers
• Queues with switchover. -- A review and critique
• Stability and optimality of a multi-product production and storage system under demand uncertainty

Cited in

(8)

• Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes
• Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm
• Robustness to incorrect system models in stochastic control
• Value set iteration for Markov decision processes
• An empirical study of policy convergence in Markov decision process value iteration
• scientific article; zbMATH DE number 4133400 (Why is no real title available?)
• Value iteration for streaming data on a continuous space with gradient method in an RKHS
• scientific article; zbMATH DE number 522741 (Why is no real title available?)

This page was built for publication: Accelerating the convergence of value iteration by using partial transition functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2355825)