Reinforcement Learning by KFM Probabilistic Associative Memory Based on Weights Distribution and Area Neuron Increase and Decrease.
Takahiro HadaYuko OsanaPublished in: ICONIP (1) (2010)
Keyphrases
- reinforcement learning
- neural network
- associative memory
- probabilistic model
- bayesian networks
- learning process
- function approximation
- input pattern
- reinforcement learning algorithms
- generative model
- gaussian distribution
- weighted sum
- linear combination
- model free
- spatial distribution
- relative importance
- random variables
- temporal difference
- data distribution
- probability distribution
- learning algorithm
- neural model
- input patterns
- posterior probability
- information theoretic
- state space
- artificial neural networks