Recurrent Control Nets for Deep Reinforcement Learning.
Vincent LiuAdemi AdenijiNathaniel LeeJason ZhaoMario SroujiPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- control system
- function approximation
- robotic control
- control method
- fuzzy logic
- state space
- control policy
- learning process
- optimal policy
- machine learning
- adaptive control
- process control
- reinforcement learning algorithms
- policy search
- evaluation function
- temporal difference
- database
- feed forward
- information systems
- data mining
- neural network