Multifidelity Reinforcement Learning with Control Variates.
Sami KhairyPrasanna BalaprakashPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- robotic control
- control strategy
- control system
- control method
- robot control
- function approximation
- learning process
- control strategies
- temporal difference
- markov decision processes
- closed loop
- principal components
- evolutionary algorithm
- artificial neural networks
- control policy
- feature selection