Time-Optimal Control via Heaviside Step-Function Approximation.
Kai PfeifferQuang-Cuong PhamPublished in: IROS (2023)
Keyphrases
- optimal control
- function approximation
- reinforcement learning
- control problems
- dynamic programming
- temporal difference
- temporal difference learning algorithms
- feedback control
- infinite horizon
- model free
- actor critic
- radial basis function
- control strategy
- policy gradient
- learning algorithm
- function approximators
- temporal difference learning
- control law
- state space
- reinforcement learning algorithms
- neural network
- optimal control problems
- action selection
- machine learning
- policy iteration
- control system
- markov decision processes
- learning tasks