Optimality and convergence of adaptive optimal control by reinforcement synthesis.
Wei-Song LinPublished in: Autom. (2011)
Keyphrases
- optimal control
- reinforcement learning
- average cost
- control problems
- dynamic programming
- control strategy
- class of nonlinear systems
- risk sensitive
- infinite horizon
- brownian motion
- convergence speed
- feedback control
- actor critic
- optimal control problems
- adaptive control
- lyapunov function
- data mining
- control law
- linear quadratic
- control method
- convergence rate
- state space
- optimal solution