Data-Driven LQR using Reinforcement Learning and Quadratic Neural Networks.
Soroush AsriLuis RodriguesPublished in: CoRR (2023)
Keyphrases
- data driven
- neural network
- reinforcement learning
- optimal control
- function approximators
- function approximation
- pattern recognition
- back propagation
- computational complexity
- artificial neural networks
- learning capabilities
- state space
- fuzzy logic
- objective function
- neural nets
- reinforcement learning algorithms
- markov decision processes
- temporal difference
- dc dc converter
- model free
- fuzzy neural network
- training process
- feed forward
- multilayer perceptron
- optimal policy
- learning process
- learning algorithm
- recurrent neural networks
- learning classifier systems
- data sets
- neural network model
- dynamic programming
- rule extraction
- cellular neural networks
- robotic control