A new family of optimal adaptive controllers for Markov chains

DOI10.1109/TAC.1982.1102878zbMath0471.93069OpenAlexW2123225686MaRDI QIDQ3926472

Arthur Becker, P. R. Kumar

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.1982.1102878

zbMATH Keywords

Markov chainsunknown transition probabilitiesinfinite operating time periodon-line control of unknown systemsoptimal adaptive controllers

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Estimation and detection in stochastic control theory (93E10) Optimal stochastic control (93E20) Continuous-time Markov processes on discrete state spaces (60J27)

Related Items

Almost self-optimizing strategies for the adaptive control of diffusion processes ⋮ On the ergodic and the adaptive control of stochastic differential delay systems ⋮ On nearly self-optimizing strategies for a discrete-time uniformly ergodic adaptive model ⋮ Self-tuning control of diffusions without the identifiability condition ⋮ Parameter estimation in stochastic systems: some recent results and applications ⋮ Stochastic $\varepsilon$-Optimal Linear Quadratic Adaptation: An Alternating Controls Policy ⋮ Controlled Sensing for Sequential Multihypothesis Testing with Controlled Markovian Observations and Non-Uniform Control Cost ⋮ The Kumar-Becker-Lin scheme revisited ⋮ Sample complexity for Markov chain self-tuner ⋮ On the Milito-Cruz adaptive control scheme for Markov chains