Turnpikes in Finite Markov Decision Processes and Random Walk

DOI10.1137/s0040585x97t991325zbMath1518.90121OpenAlexW4368347445MaRDI QIDQ6160489

Aleksey B. Piunovskiy

Publication date: 10 May 2023

Published in: Theory of Probability & Its Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0040585x97t991325

zbMATH Keywords

Markov decision processturnpikerandom walkaverage rewardstochastic knapsack problemdiscounted reward

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Combinatorial optimization (90C27) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An adaptive stochastic knapsack problem
• A forecast horizon and a stopping rule for general Markov decision processes
• Turnpike properties in the calculus of variations and optimal control
• Examples in Markov Decision Processes
• Approximating the Stochastic Knapsack Problem: The Benefit of Adaptivity
• A Turnpike Theorem For A Risk-Sensitive Markov Decision Process with Stopping
• MARKOV DECISION PROCESSES WITH RANDOM HORIZON
• Decision Horizons in Discrete Time Undiscounted Markov Renewal Programming
• Uniform Turnpike Theorems for Finite Markov Decision Processes
• Turnpike Theory for the Robinson–Solow–Srinivasan Model
• Controlled Random Walk: Conjecture and Counter-Example
• Algorithms for Countable State Markov Decision Models with an Absorbing Set
• Turnpike Planning Horizons for a Markovian Decision Model
• On Finding the Maximal Gain for Markov Decision Processes
• Markov Decision Processes with Slow Scale Periodic Decisions

This page was built for publication: Turnpikes in Finite Markov Decision Processes and Random Walk