Entropy-maximizing TD3-based reinforcement learning for adaptive PID control of dynamical systems.
Myisha A. ChowdhurySaif S. S. Al-WahaibiQiugang LuPublished in: Comput. Chem. Eng. (2023)
Keyphrases
- dynamical systems
- reinforcement learning
- pid control
- state space
- adaptive control
- temporal difference
- reinforcement learning algorithms
- function approximation
- reinforcement learning methods
- rbfnn
- fuzzy control
- predictive state representations
- differential equations
- control law
- control theory
- feedback control
- nonlinear dynamical systems
- pid controller
- control method
- function approximators
- control algorithm
- control system
- optimal control
- model free
- linear systems
- markov decision processes
- transfer learning
- partially observable markov decision processes
- learning algorithm
- neural network
- real time
- control strategy
- closed loop
- learning tasks
- optimal policy
- supervised learning
- dynamic programming