Login / Signup
Online policy iterations for optimal control of input-saturated systems.
Simone Baldi
Giorgio Valmorbida
Antonis Papachristodoulou
Elias B. Kosmatopoulos
Published in:
ACC (2016)
Keyphrases
</>
optimal control
infinite horizon
average cost
control problems
reinforcement learning
actor critic
class of nonlinear systems
control strategy
feedback control
lyapunov function
risk sensitive
real time
brownian motion