Federico
Federico
Hello, thank you for sharing your work! Is there a way of extracting 3D keypoints based on the reconstructed mesh?
Hi, I was thinking it could be useful to add an option to enable the essential trackers from the persistent notification, in addition to enabling all the trackers for a...
### Question Hello, is it possible to create a custom action space to use with PPO? From what I read in the documentation, there are limited `Space` instances allowed. But...

Hello, I wanted to train a different character (like you did with the Atlas robot) and I am trying to figure out what changes I need to implement. I am...
Hello, how did you estimate the values of kp and kd for the humanoid? If I were to develop a different model, how could I estimate the 2 parameters?
Hi, how do you calculate the distribution of the mass over the different segments? Did you use any reference from the literature? The only thing the paper mentions is the...
Hello, I am trying to implement the skill selector for switching between multiple clips. I came up with two different options on how to implement it: 1) sampling when calling...
Hello, I tried training the character with the multiclip reward as described in the paper. However, the reward reaches a [plateau](https://drive.google.com/file/d/1QnWDl9k9QIxauE9h4NTgNyXYGQXa1yCS/view?usp=sharing) and the character limps. Do you have any suggestion...
Hello, I was wondering if you ever trained your multi-clip reward with motions that have different durations (e.g., one motion of 3 seconds and one motion of 8 seconds) and...