The Adaptive PID Controlling Algorithm Using Asynchronous Advantage Actor-Critic Learning Method.
Qifeng SunHui RenYouxiang DuanYanan YanPublished in: SimuTools (2019)
Keyphrases
- actor critic
- dynamic programming
- learning algorithm
- computational complexity
- gradient method
- optimization algorithm
- cost function
- reinforcement learning
- recursive least squares
- k means
- objective function
- model free
- mathematical model
- support vector machine svm
- policy gradient
- control system
- negative matrix factorization
- convergence rate
- optimization method
- neuro fuzzy
- monte carlo
- search space
- approximate dynamic programming
- neural network
- adaptive filtering
- reinforcement learning algorithms
- optimal control
- learning problems
- np hard