Login / Signup
CACTO-SL: Using Sobolev learning to improve continuous actor-critic with trajectory optimization.
Elisa Alboni
Gianluigi Grandesso
Gastone Pietro Rosati Papini
Justin Carpentier
Andrea Del Prete
Published in:
L4DC (2024)
Keyphrases
</>
actor critic
reinforcement learning
learning algorithm
optimization problems
policy gradient
machine learning
active learning
control system
dynamic environments
optimal control