An adaptive optimal controller for discrete-time Markov environments
- 31 August 1977
- journal article
- Published by Elsevier in Information and Control
- Vol. 34 (4) , 286-295
- https://doi.org/10.1016/s0019-9958(77)90354-0
Abstract
No abstract availableKeywords
This publication has 7 references indexed in Scilit:
- On the Asymptotic Performances of Finite-State Two-Armed Bandit ControllersIEEE Transactions on Systems, Man, and Cybernetics, 1974
- Punish/Reward: Learning with a Critic in Adaptive Threshold SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1973
- Finite-Time Performance of Some Two-Armed Bandit ControllersIEEE Transactions on Systems, Man, and Cybernetics, 1973
- Human operators and automatic adaptive controllers: A comparative study on a particular control taskInternational Journal of Man-Machine Studies, 1973
- The two-armed-bandit problem with time-invariant finite memoryIEEE Transactions on Information Theory, 1970
- Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance CriteriaIEEE Transactions on Systems Science and Cybernetics, 1969
- Non-Cooperative GamesAnnals of Mathematics, 1951