PPO has long dominated robot locomotion training in simulation.
Robotic Systems Lab
Visit on X@leggedrobotics39K followers
46,029 views
PPO has long dominated robot locomotion training in simulation. SAC, despite its sample efficiency, couldn't keep up.
We analyze why:
🔗
🔥Integrated into RSL-RL, our approach requires only minimal changes, making SAC a drop-in alternative out of the box.
Comments
Comments from the original post on X (Twitter)
No comments yet
