Two ?-Optimal Nonlinear Reinforcement Schemes for Stochastic Automata
- 1 January 1974
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. SMC-4 (1) , 126-131
- https://doi.org/10.1109/TSMC.1974.5408538
Abstract
Two nonlinear reinforcement schemes [2], [8] for variable-structure stochastic automata are discussed. It is proved that they can ensure ε-optimality under certain conditions.Keywords
This publication has 6 references indexed in Scilit:
- Optimal non-linear reinforcement schemes for stochastic automataInformation Sciences, 1972
- Stochastic Automata GamesIEEE Transactions on Systems Science and Cybernetics, 1969
- Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance CriteriaIEEE Transactions on Systems Science and Cybernetics, 1969
- On the linear model with two absorbing barriersJournal of Mathematical Psychology, 1968
- On Expediency and Convergence in Variable-Structure AutomataIEEE Transactions on Systems Science and Cybernetics, 1968
- A stochastic automaton model for the synthesis of learning systemsIEEE Transactions on Systems Science and Cybernetics, 1966