Observer-Feedback-Feedforward Controller Structures in Reinforcement Learning.
Ruoqi ZhangPer MattssonTorbjörn WigrenPublished in: CoRR (2023)
Keyphrases
- feed forward
- reinforcement learning
- adaptive neural
- neural network
- back propagation
- neural nets
- hidden layer
- artificial neural networks
- visual cortex
- recurrent neural networks
- optimal control
- control policy
- learning algorithm
- function approximation
- activation function
- biologically plausible
- artificial neural
- neural architecture
- real time
- primate visual cortex
- state space
- adaptive control
- closed loop
- optimal policy
- image sequences
- recurrent networks
- visual motion
- machine learning
- control system
- artificial intelligence
- knowledge base
- feedback control
- markov decision processes