A Training Algorithm for Systems Described by Stochastic Transition Matrices
- 1 January 1971
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. SMC-1 (1) , 86-87
- https://doi.org/10.1109/TSMC.1971.5408611
Abstract
Stochastic transition matrices are a convenient means for describing the behavior of adaptive and learning systems. Several systems which utilize these matrices and associated reinforcement (reward and punishment) techniques have been reported. A training algorithm is described which has been applied to a learning system described by stochastic transition matrices in which the environment was unknown a priori and nonstationary.Keywords
This publication has 4 references indexed in Scilit:
- Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance CriteriaIEEE Transactions on Systems Science and Cybernetics, 1969
- 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
- Stochastic models for learning.Published by American Psychological Association (APA) ,1955