Optimal adaptive controllers for unknown Markov chains

DOI10.1109/TAC.1982.1103017MaRDI QIDQ3950406zbMATH OpenOpenAlexFDO

Authors P. R. Kumar, Woei Lin

Publication date 1982

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tac.1982.1103017

zbMATH Keywords

adaptive controllersoptimal performanceunknown Markov chain

Mathematics Subject Classification ID

Continuous-time Markov processes on discrete state spaces (60J27) Adaptive control/observation systems (93C40) Stochastic systems in control theory (general) (93E03) Optimal stochastic control (93E20)

Cited in

(10)

• An optimal stopping time problem with time average cost in a bounded interval
• Ergodic and adaptive control of nearest-neighbor motions
• On the Milito-Cruz adaptive control scheme for Markov chains
• An incremental off-policy search in a model-free Markov decision process using a single sample path
• The Kumar-Becker-Lin scheme revisited
• Stochastic \varepsilon-Optimal Linear Quadratic Adaptation: An Alternating Controls Policy
• Ergodic control of multidimensional diffusions. II: Adaptive control
• Adaptive service rate control of an M/M/1 queue with server breakdowns
• Self-tuning control of diffusions without the identifiability condition
• Adaptive control of Markov chains with local updates

This page was built for publication: Optimal adaptive controllers for unknown Markov chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3950406)