A unified approach to time-aggregated Markov decision processes

DOI10.1016/J.AUTOMATICA.2015.12.022zbMATH Open1335.93149OpenAlexW2293893700MaRDI QIDQ259403FDOQ259403

Yanjie Li, Xinyu Wu

Publication date: 11 March 2016

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2015.12.022

Recommendations

• A time aggregation approach to Markov decision processes
• Time aggregated Markov decision processes via standard dynamic programming
• A unified approach to adaptive control of average reward Markov decision processes
• Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm
• A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases

zbMATH Keywords

Markov decision processperformance sensitivitysemi-Markov decision processtime aggregation

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Perturbation realization, potentials, and sensitivity analysis of Markov processes
• Continuous-time Markov decision processes. Theory and applications
• A time aggregation approach to Markov decision processes
• A basic formula for performance gradient estimation of semi-Markov decision processes
• Performance gradient estimation for the very large finite Markov chains
• Title not available (Why is that?)
• A New Value Iteration method for the Average Cost Dynamic Programming Problem
• Semi-markov decision problems and performance sensitivity analysis
• Markov decision Processes with fractional costs
• Incremental Value Iteration for Time-Aggregated Markov-Decision Processes
• Title not available (Why is that?)
• Title not available (Why is that?)
• Recent advances in hierarchical reinforcement learning
• Time aggregated Markov decision processes via standard dynamic programming

Cited In (4)

• Sliding mode control for semi-Markovian jump systems via output feedback
• A time aggregation approach to Markov decision processes
• A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases
• Coupling based estimation approaches for the average reward performance potential in Markov chains

This page was built for publication: A unified approach to time-aggregated Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q259403)