A Foremost-Policy Reinforcement Learning Based ART2 Neural Network and Its Learning Algorithm.
Jian FanGengfeng WuPublished in: ISNN (1) (2005)
Keyphrases
- reinforcement learning
- art neural network
- learning algorithm
- optimal policy
- rl algorithms
- policy search
- adaptive resonance theory
- reinforcement learning algorithms
- action selection
- function approximators
- model free
- function approximation
- reward function
- neural network
- state space
- control policy
- markov decision processes
- machine learning
- learning problems
- fuzzy artmap
- web usage data
- learning process
- training data
- reward signal
- back propagation
- supervised learning
- temporal difference
- active learning
- fuzzy clustering
- web search