realquantumcookie / aprl

Efficient Real-World RL for Legged Locomotion via Adaptive Policy Regularization

Hi there 👋 Yunhao Cao (Quantum Cookie) Here

🔗 Website

🔗 LinkedIn

aprl's Issues

How to reproduce 0.44m/s "Restricted"?

Dear author:
Thanks a lot for inventing APRL and open sourcing an official implementation.

I have a question about the performance of "Restricted".
Fig 3 in [46]Demonstrating a walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning showed that robot can move on the flat ground at an average speed of 0.06m/s after 20min.
Fig 6. in the APRL paper showed that robot can move on the flat ground at an average speed of 0.44m/s after 20min.

There is a 7x difference. I have noticed that the APRL paper used Go1 while [46] used A1, and different velocity measurement might be applied (tracking camera vs. Kalman filter). I want to know if there is any other difference between "Restricted" and [46].

Thanks!