Actor-Critic Reinforcement Learning for Control with Stability Guarantee.
Minghao HanLixian ZhangJun WangWei PanPublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- lyapunov stability
- control problems
- temporal difference
- policy gradient
- lyapunov function
- reinforcement learning algorithms
- approximate dynamic programming
- function approximation
- neuro fuzzy
- gradient method
- control strategy
- dynamic programming
- policy iteration
- control policy
- markov decision processes
- control strategies
- neural network
- state space
- control system
- reinforcement learning methods
- natural actor critic
- action selection
- inverted pendulum
- multi agent
- partially observable markov decision processes
- adaptive control
- model free
- least squares
- machine learning