OPTIMAL MIXING OF MARKOV DECISION RULES FOR MDP CONTROL

DOI10.1017/S0269964811000039zbMath1228.90149OpenAlexW2160062319MaRDI QIDQ3100881

Dinard van der Laan

Publication date: 22 November 2011

Published in: Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1017/s0269964811000039

zbMATH Keywords

nonstationary policiesfinite number of Markov decision rules

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items

Assigning multiple job types to parallel specialized servers

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Discrete-event control of stochastic networks: multimodularity and regularity.
• Fraenkel's conjecture for six sequences
• Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes
• Measure-valued differentiation for Markov chains
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
• Multimodularity, Convexity, and Optimization Properties
• Optimal Search for a Moving Target
• Markov Decision Problems and State-Action Frequencies
• ON THE OPTIMAL OPEN-LOOP CONTROL POLICY FOR DETERMINISTIC AND EXPONENTIAL POLLING SYSTEMS
• Balanced sequences and optimal routing
• Extremal Splittings of Point Processes
• Randomized and Past-Dependent Policies for Markov Decision Processes with Multiple Constraints
• The Maclaurin series for performance functions of Markov chains
• Taylor series expansions for stationary Markov chains
• On the static assignment to parallel servers
• Gradient estimation for discrete-event systems by measure-valued differentiation
• On the Average Waiting Time for Regular Routing to Deterministic Queues
• Symbolic Dynamics II. Sturmian Trajectories