Value iteration and adaptive optimal control for linear continuous-time systems.
Tao BianZhong-Ping JiangPublished in: RAM/CIS (2015)
Keyphrases
- optimal control
- dynamic programming
- infinite horizon
- feedback control
- control problems
- class of nonlinear systems
- optimal control problems
- control strategy
- reinforcement learning
- state space
- linear systems
- policy iteration
- risk sensitive
- learning algorithm
- machine learning
- brownian motion
- dynamical systems
- optimal policy
- control law
- adaptive control