A unified approach to time-aggregated Markov decision processes

DOI10.1016/j.automatica.2015.12.022zbMath1335.93149OpenAlexW2293893700MaRDI QIDQ259403

Yan-Jie Li, Xin-Yu 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

zbMATH Keywords

Markov decision processsemi-Markov decision processperformance sensitivitytime aggregation

Mathematics Subject Classification ID

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

Related Items (2)

Sliding mode control for semi-Markovian jump systems via output feedback ⋮ Coupling based estimation approaches for the average reward performance potential in Markov chains

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Time aggregated Markov decision processes via standard dynamic programming
• 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
• Perturbation realization, potentials, and sensitivity analysis of Markov processes
• 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
• Recent advances in hierarchical reinforcement learning

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