Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems.
Vasanth ReddyHoda EldardiryAlmuatazbellah BokerPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- control system
- optimal control
- dynamic programming
- state space
- neural network
- machine learning
- stochastic control
- function approximation
- critical points
- action selection
- robotic control
- data sets
- continuous state
- control policy
- reinforcement learning algorithms
- closed form
- transfer learning
- worst case
- optimal solution
- learning algorithm