Adaptive control of Markov chains, I: Finite parameter set
From MaRDI portal
Publication:3206798
DOI10.1109/TAC.1979.1102191zbMath0416.93065OpenAlexW2115597380MaRDI QIDQ3206798
Vivek S. Borkar, Pravin P. Varaiya
Publication date: 1979
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/tac.1979.1102191
Adaptive control/observation systems (93C40) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Stochastic systems in control theory (general) (93E03)
Related Items (16)
Bounds for the regret loss in dynamic programming under adaptive control ⋮ Adaptive LQ control: Conflict between identification and control ⋮ Estimation and control in discounted stochastic dynamic programming ⋮ Self-tuning control of diffusions without the identifiability condition ⋮ Parameter estimation in stochastic systems: some recent results and applications ⋮ Adaptive control of Markov chains with local updates ⋮ Ergodic and adaptive control of nearest-neighbor motions ⋮ Unnamed Item ⋮ On Incomplete Learning and Certainty-Equivalence Control ⋮ The Kumar-Becker-Lin scheme revisited ⋮ Revisiting the ODE method for recursive algorithms: fast convergence using quasi stochastic approximation ⋮ Sample complexity for Markov chain self-tuner ⋮ A perspective on convergence of adaptive control algorithms ⋮ Will the self-tuning approach work for general cost criteria? ⋮ On the Milito-Cruz adaptive control scheme for Markov chains ⋮ A note on the structure of two subsets of the parameter space in adaptive control problems
This page was built for publication: Adaptive control of Markov chains, I: Finite parameter set