Login / Signup
Actor-Critic Off-Policy Learning for Optimal Control of Multiple-Model Discrete-Time Systems.
Jan Skach
Bahare Kiumarsi
Frank L. Lewis
Ondrej Straka
Published in:
IEEE Trans. Cybern. (2018)
Keyphrases
</>
optimal control
actor critic
reinforcement learning
learning algorithm
mathematical model
control strategy
real time
gradient method
neural network
objective function
control system
cost function
linear programming
dynamical systems
function approximation