Stochastic approximations for finite-state Markov chains

DOI10.1016/0304-4149(90)90120-HzbMath0718.60074OpenAlexW2003308588WikidataQ59313627 ScholiaQ59313627MaRDI QIDQ2639435

Adam Shwartz, Armand M. Makowski, Dye-Jyun Ma

Publication date: 1990

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0304-4149(90)90120-h

zbMATH Keywords

adaptive controlMarkov decision problemsqueueing systemsstochastic approximations

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Optimal stochastic control (93E20) Stochastic approximation (62L20)

Related Items

Reference points and learning, Asynchronous stochastic approximation with differential inclusions, On recursive estimation for hidden Markov models, Optimal control of variable rate coding with incomplete observation in integrated voice/data packet networks, Online EM algorithm for mixture with application to Internet traffic modeling, Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning, Fundamental design principles for reinforcement learning algorithms

Cites Work

• K competing queues with geometric service requirements and linear costs: The \(\mu\) c-rule is always optimal
• Optimal policies for controlled Markov chains with a constraint
• Optimal priority assignment with hard constraint
• Comparing Policies in Markov Decision Processes: Mandl's Lemma Revisited
• Two competing queues with linear costs and geometric service requirements: the μc-rule is often optimal
• Applications of a Kushner and Clark lemma to general classes of stochastic algorithms
• Optimal priority assignment: a time sharing approach
• Constrained admission control to a queueing system
• Estimation and control in Markov chains
• A Stochastic Approximation Method
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item