Neural H₂ Control Using Continuous-Time Reinforcement Learning.
Adolfo PerrusquíaWen YuPublished in: IEEE Trans. Cybern. (2022)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- robot control
- state space
- control policy
- control system
- dynamic programming
- optimal policy
- control strategy
- neural network
- learning algorithm
- iterative learning control
- control theory
- control method
- function approximation
- network architecture
- adaptive control
- action selection
- data acquisition
- markov decision processes
- markov decision process
- dynamical systems
- markov chain
- learning process
- fitted q iteration