Reinforcement learning with internal expectation in the random neural networks for cascaded decisions

BioSystems

Volumn 63, Issue 1-3, 2001, Pages 21-34

  Halici, Ugur ^a  

^a MIDDLE EAST TECHNICAL UNIVERSITY   (Turkey)

Author keywords

Cascaded decisions; Extinction; Neural networks; Random neural networks; Reinforcement learning

Indexed keywords

ARTIFICIAL NEURAL NETWORK;

ARTICLE; ENVIRONMENT; EXPECTATION; LEARNING; MODEL; NERVE CELL; NERVE CELL NETWORK; PUNISHMENT; REINFORCEMENT; REWARD; SIMULATION;

EID: 0034813305     PISSN: 03032647     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0303-2647(01)00144-7     Document Type: Article

References (27)

1. Recognition algorithm using evolutionary learning on the random neural networks
2. Learning and Sequential Decision Making
3. A digital neuron realization for the random neural network model
4. An Application of Stochastic Automata to the Synthesis Learning Systems
5. Random neural networks with positive and negative signals and product form solution
6. Stability of the random neural network model
7. Learning in the recurrent random neural network
8. Special issue on G networks
9. Global behavior of homogenous random neural systems
10. Reward, punishment and expectation in reinforcement learning for the random neural networks
11. Reinforcement learning in random neural networks for cascaded decisions
12. Reinforcement learning with internal expectation for the random neural networks
13. A linear approximation for the Gelenbe's learning algorithm for recurrent random neural networks
14. Learning to predict the methods of temporal difference
15. Comparison of expedient and optimal reinforcement schemes for learning systems
16. Algorithms for changing automaton transition probabilities
17. Q-learning