A Barrier-Lyapunov Actor-Critic Reinforcement Learning Approach for Safe and Stable Control.
Liqun ZhaoKonstantinos GatsisAntonis PapachristodoulouPublished in: CoRR (2023)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- adaptive control
- control problems
- temporal difference
- control theory
- policy gradient
- approximate dynamic programming
- control law
- reinforcement learning algorithms
- function approximation
- lyapunov function
- control strategy
- control system
- control policy
- neuro fuzzy
- control method
- gradient method
- policy iteration
- dynamic programming
- nonlinear systems
- dynamical systems
- rl algorithms
- model free
- action selection
- machine learning
- control scheme
- policy gradient methods
- recurrent neural networks
- state space
- control strategies
- closed loop
- supervised learning
- robot manipulators
- sufficient conditions
- optimal policy
- monte carlo
- multi agent
- evaluation function