Bias optimality and strong \(n\) \((n= -1,0)\) discount optimality for Markov decision processes

DOI10.1016/j.jmaa.2007.01.002zbMath1194.93226OpenAlexW2062820819MaRDI QIDQ2371871

Quanxin Zhu

Publication date: 9 July 2007

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmaa.2007.01.002

zbMATH Keywords

optimal stationary policybias optimalityaverage rewarddiscrete-time Markov decision processstrong 0-discount optimality

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40) Transition functions, generators and resolvents (60J35)

Related Items

Policy iteration algorithms for zero-sum stochastic differential games with long-run average payoff criteria ⋮ Average optimality for continuous-time Markov decision processes with a policy iteration approach ⋮ Discount-sensitive equilibria in zero-sum stochastic differential games

Cites Work

• Markov decision processes with a minimum-variance criterion
• Strong 1-optimal stationary policies in denumerable Markov decision processes
• Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards
• A note on strong 1-optimal policies in Markov decision chains with unbounded costs
• The relations among potentials, perturbation analysis, and Markov decision processes
• Bias optimality versus strong 0-discount optimality in Markov control processes with unbounded costs
• Adaptive Markov control processes
• Another set of conditions for Markov decision processes with average sample-path costs
• Unbounded cost Markov decision processes with limsup and liminf average criteria: new conditions
• Average optimality for Markov decision processes in borel spaces: a new condition and approach
• Perturbation realization, potentials, and sensitivity analysis of Markov processes
• Bias Optimality in Controlled Queueing Systems
• Strong 0-discount optimal policies in a Markov decision process with a Borel state space
• Sample-Path Optimality and Variance-Minimization of Average Cost Markov Control Processes
• Discrete Dynamic Programming
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria
• Another Set of Conditions for Strongn(n = −1, 0) Discount Optimality in Markov Decision Processes
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item