Login / Signup

Value learning from trajectory optimization and Sobolev descent: A step toward reinforcement learning with superlinear convergence properties.

Amit ParagSébastien KleffLéo SaciNicolas MansardOlivier Stasse
Published in: ICRA (2022)
Keyphrases
  • reinforcement learning
  • learning algorithm
  • machine learning
  • learning tasks
  • supervised learning
  • optimization problems
  • function approximation