Actor-Critic Reinforcement Learning Control of Non-Strict Feedback Nonaffine Dynamic Systems.
Xiangwei BuPublished in: IEEE Access (2019)
Keyphrases
- dynamic systems
- actor critic
- reinforcement learning
- optimal control
- discrete event
- control problems
- complex systems
- linear time invariant
- temporal difference
- policy gradient
- approximate dynamic programming
- dynamical systems
- gradient method
- neuro fuzzy
- function approximation
- control strategy
- feedback control
- consistency based diagnosis
- reinforcement learning algorithms
- state space
- control policy
- state variables
- control system
- adaptive control
- dynamic programming
- markov decision processes
- policy iteration
- control strategies
- particle filter
- control method
- model free
- learning algorithm
- average reward
- action selection
- policy gradient methods
- action space
- continuous variables
- markov decision process
- convergence rate
- reinforcement learning methods
- partially observable
- markov chain
- multi agent