Login / Signup
Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle.
Marc Peter Deisenroth
Toshiyuki Ohtsuka
Florian Weissel
Dietrich Brunn
Uwe D. Hanebeck
Published in:
MFI (2006)
Keyphrases
</>
finite horizon
feedback control
optimal control
infinite horizon
stochastic systems
optimal policy
state space
dynamic programming
markov decision process
markov decision processes
closed loop
multistage
average cost
adaptive control
machine learning
learning algorithm
np hard
optimal solution