On strong average optimality of Markov decision processes with unbounded costs

DOI10.1016/0167-6377(92)90040-AMaRDI QIDQ1197886zbMATH OpenOpenAlexFDO

Authors Mrinal K. Ghosh, Steven I. Marcus

Publication date 16 January 1993

Published in Operations Research Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0167-6377(92)90040-a

zbMATH Keywords

average Markov decision processescompact action spacecountable state spacestable stationary strategystrong average optimal

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• A condition for strong average optimality of MDP with non-uniformly bounded costs
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• scientific article; zbMATH DE number 4102842
• A new condition for the existence of optimal stationary policies in average cost Markov decision processes
• Average cost Markov decision processes with weakly continuous transition probabilities

Cites work

• A Solution to a Countable System of Equations Arising in Markovian Decision Processes
• Adaptive Markov control processes
• Average cost Markov decision processes: Optimality conditions
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• Average Cost Semi-Markov Decision Processes and the Control of Queueing Systems
• Comparing recent assumptions for the existence of average optimal stationary policies
• Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming Equations
• Cumulative quantum work-deficit versus entanglement in the dynamics of an infinite spin chain
• Denumerable State Markovian Decision Processes-Average Cost Criterion
• Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded Rewards
• Ergodic and adaptive control of nearest-neighbor motions
• scientific article; zbMATH DE number 3122709 (Why is no real title available?)
• scientific article; zbMATH DE number 3906232 (Why is no real title available?)
• scientific article; zbMATH DE number 4085565 (Why is no real title available?)
• scientific article; zbMATH DE number 4102842 (Why is no real title available?)
• scientific article; zbMATH DE number 32015 (Why is no real title available?)
• scientific article; zbMATH DE number 49674 (Why is no real title available?)
• scientific article; zbMATH DE number 3445938 (Why is no real title available?)
• Necessary conditions for the optimality equation in average-reward Markov decision processes
• On Minimum Cost Per Unit Time Control of Markov Chains
• On optimality criteria for dynamic programs with long finite horizons
• Optimal control of service rates in networks of queues
• Semi-Markov Decision Processes with Unbounded Rewards
• Stochastic optimal control. The discrete time case

Cited in

(20)

• Average optimality in dynamic programming on Borel spaces -- unbounded costs and controls
• A note on strong 1-optimal policies in Markov decision chains with unbounded costs
• The value iteration method for countable state Markov decision processes
• Optimal average value convergence in nonhomogeneous Markov decision processes
• Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
• A new strong optimality criterion for nonstationary Markov decision processes
• The convergence of value iteration in average cost Markov decision chains
• Unbounded cost Markov decision processes with limsup and liminf average criteria: new conditions
• An average-value-at-risk criterion for Markov decision processes with unbounded costs
• A condition for strong average optimality of MDP with non-uniformly bounded costs
• Existenz durelisehnittsoptimaler Strategien in einem Markoffschen Entscheidungsmodell mit unbekaimter Parameterfolge
• scientific article; zbMATH DE number 4102842 (Why is no real title available?)
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• scientific article; zbMATH DE number 513084 (Why is no real title available?)
• Denumerable controlled Markov chains with average reward criterion: Sample path optimality
• scientific article; zbMATH DE number 2096692 (Why is no real title available?)
• Strong average optimality criterion for continuous-time Markov decision processes
• On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs
• scientific article; zbMATH DE number 238320 (Why is no real title available?)
• Uniqueness and Stability of Optimal Policies of Finite State Markov Decision Processes

This page was built for publication: On strong average optimality of Markov decision processes with unbounded costs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1197886)