Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm

DOI10.1016/J.EJOR.2014.08.023MaRDI QIDQ300040zbMATH OpenOpenAlexFDO

Authors E. F. Arruda, Marcelo Dutra Fragoso

Publication date 23 June 2016

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

Full work available at URL https://doi.org/10.1016/j.ejor.2014.08.023

zbMATH Keywords

dynamic programmingembeddingstochastic optimal controlMarkov decision processestime aggregation

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• A time aggregation approach to Markov decision processes
• Reinforcement learning based algorithms for average cost Markov decision processes
• A unified approach to time-aggregated Markov decision processes
• Time aggregated Markov decision processes via standard dynamic programming
• The control of a two-level Markov decision process by time aggregation

Cites work

• scientific article; zbMATH DE number 1315585 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems
• A New Value Iteration method for the Average Cost Dynamic Programming Problem
• A time aggregation approach to Markov decision processes
• Accelerating the convergence of value iteration by using partial transition functions
• An analysis of temporal-difference learning with function approximation
• Approximate Dynamic Programming
• Approximate dynamic programming via direct search in the space of value function approximations
• Approximate dynamic programming with a fuzzy parameterization
• Dynamic programming and optimal control. Vol. 2
• Exact finite approximations of average-cost countable Markov decision processes
• Incremental Value Iteration for Time-Aggregated Markov-Decision Processes
• Kernel-based reinforcement learning
• LAO*: A heuristic search algorithm that finds solutions with loops
• Lebesgue-Sampling-Based Optimal Control Problems With Time Aggregation
• Markov decision Processes with fractional costs
• Performance gradient estimation for the very large finite Markov chains
• Probabilistic relational planning with first order decision diagrams
• Reducing reinforcement learning to KWIK online regression
• Simulation-based algorithms for Markov decision processes.
• Stability and optimality of a multi-product production and storage system under demand uncertainty
• Sufficient Classes of Strategies in Discrete Dynamic Programming I: Decomposition of Randomized Strategies and Embedded Models
• Time aggregated Markov decision processes via standard dynamic programming

Cited in

(4)

• A unified approach to time-aggregated Markov decision processes
• Time aggregated Markov decision processes via standard dynamic programming
• A time aggregation approach to Markov decision processes
• The control of a two-level Markov decision process by time aggregation

Describes a project that uses

Uses Software

• FODD-Planner

This page was built for publication: Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q300040)