On-Line EM Reinforcement Learning.
Junichiro YoshimotoShin IshiiMasa-aki SatoPublished in: IJCNN (3) (2000)
Keyphrases
- reinforcement learning
- expectation maximization
- em algorithm
- function approximation
- unsupervised learning
- state space
- markov decision processes
- multi agent
- learning algorithm
- control system
- probabilistic model
- temporal difference
- gaussian mixture model
- reinforcement learning algorithms
- k means
- bayesian framework
- mixture model
- optimal policy
- robotic control
- model free
- real robot
- multi agent reinforcement learning
- policy search
- expectation maximisation
- data sets
- gaussian mixture
- optimal control
- learning problems
- dynamical systems
- maximum likelihood
- supervised learning
- image segmentation
- data mining