Cross-Entropy Optimization of Control Policies With Adaptive Basis Functions.
Lucian BusoniuDamien ErnstBart De SchutterRobert BabuskaPublished in: IEEE Trans. Syst. Man Cybern. Part B (2011)
Keyphrases
- basis functions
- cross entropy
- control policies
- error function
- linear combination
- state space
- log likelihood
- radial basis function
- action space
- maximum likelihood
- control policy
- optimal policy
- language modeling
- evaluation metrics
- reinforcement learning
- activation function
- artificial neural networks
- reward function
- language model
- small number
- mobile robot
- optimal solution
- motion control
- neural network
- set of basis functions