Login / Signup
Model-based reinforcement learning for output-feedback optimal control of a class of nonlinear systems.
Ryan Self
Michael Harlan
Rushikesh Kamalapurkar
Published in:
ACC (2019)
Keyphrases
</>
class of nonlinear systems
optimal control
model based reinforcement learning
reinforcement learning
markov decision processes
dynamic programming
feedback control
control law
control strategy
infinite horizon
state space
optimal control problems
neural network
average cost