Reinforcement Learning

CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization
Trajectory Optimization (TO) and Reinforcement Learning (RL) are powerful and complementary tools to solve optimal control problems. On …
Elisa Alboni, Gianluigi Grandesso, Gastone P. Rosati Papini, Justin Carpentier, Andrea Del Prete
Cite arXiv Video Code
CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization
CACTO: Continuous Actor-Critic With Trajectory Optimization - Towards Global Optimality
This letter presents a novel algorithm for the continuous control of dynamical systems that combines Trajectory Optimization (TO) and …
Gianluigi Grandesso, Elisa Alboni, Gastone P.Rosati Papini, Patrick M. Wensing, Andrea Del Prete
Cite DOI arXiv
CACTO: Continuous Actor-Critic With Trajectory Optimization - Towards Global Optimality
Optimization and Learning for Robot Control
A 48-hour course for master students focusing on modern optimal control and reinforcement learning techniques for robot control
Jan 1, 2020
Code Slides Video
Optimization and Learning for Robot Control