CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization

1 code implementation • 17 Dec 2023 • Elisa Alboni, Gianluigi Grandesso, Gastone Pietro Rosati Papini, Justin Carpentier, Andrea Del Prete

Recently, we have proposed CACTO (Continuous Actor-Critic with Trajectory Optimization), an algorithm that uses TO to guide the exploration of an actor-critic RL algorithm.

Reinforcement Learning (RL)