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

DOI10.1016/j.ejor.2014.08.023zbMath1338.90443OpenAlexW2072370473MaRDI QIDQ300040

Marcelo Dutra Fragoso, Edilson F. Arruda

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 programmingMarkov decision processesembeddingstochastic optimal controltime aggregation

Mathematics Subject Classification ID

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

Uses Software

• FODD-Planner

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reducing reinforcement learning to KWIK online regression
• Time aggregated Markov decision processes via standard dynamic programming
• Approximate dynamic programming via direct search in the space of value function approximations
• Simulation-based algorithms for Markov decision processes.
• Approximate dynamic programming with a fuzzy parameterization
• Kernel-based reinforcement learning
• A time aggregation approach to Markov decision processes
• Accelerating the convergence of value iteration by using partial transition functions
• Exact finite approximations of average-cost countable Markov decision processes
• Stability and optimality of a multi-product production and storage system under demand uncertainty
• Probabilistic Relational Planning with First Order Decision Diagrams
• Sufficient Classes of Strategies in Discrete Dynamic Programming I: Decomposition of Randomized Strategies and Embedded Models
• Performance gradient estimation for the very large finite Markov chains
• An analysis of temporal-difference learning with function approximation
• A New Value Iteration method for the Average Cost Dynamic Programming Problem
• A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems
• Markov decision Processes with fractional costs
• Incremental Value Iteration for Time-Aggregated Markov-Decision Processes
• Approximate Dynamic Programming
• Lebesgue-Sampling-Based Optimal Control Problems With Time Aggregation
• LAO*: A heuristic search algorithm that finds solutions with loops

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