Control of Discrete-Time Chaotic Systems with Policy-Based Deep Reinforcement Learning.
Junya IkemotoToshimitsu UshioPublished in: IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (2020)
Keyphrases
- chaotic systems
- reinforcement learning
- adaptive control
- control policy
- optimal policy
- action selection
- initial conditions
- optimal control
- control method
- robust stability
- policy search
- control system
- nonlinear systems
- learning algorithm
- reward function
- markov decision process
- function approximation
- control strategies
- action space
- state space
- sliding mode control
- model free
- fixed point
- policy iteration
- feedback control
- function approximators
- policy gradient