Reinforcement Learning for Model Building and Variance-penalized Control.
Abhijit GosaviPublished in: WSC (2009)
Keyphrases
- reinforcement learning
- control problems
- robot control
- control system
- control policy
- multi agent
- optimal control
- machine learning
- maximum likelihood
- control method
- function approximation
- loss function
- data sets
- control policies
- adaptive control
- least squares
- state space
- covariance matrix
- reinforcement learning algorithms
- learning process
- feature selection
- real time
- low variance