Jump

Jump copied to clipboard

after 12000 times of training, run evaluate.py, the render is different from that in the video, and there is no run-up process. Is there a problem with my parameter setting?

wp133716

Hi, I found your paper very interesting! I found training p-vae(train_pose_vae.py) and training ppo for motion control (train.py). Can you tell me which part of the released code is about...

sunny-Codes

I cannot get the result the same as the paper. When the training of jump policy, I always gets reward 0. The default values to learn runup policy are: algorithm.max_iterations:...

fredericgo

Hi, I noticed that you used a layer size of 200 for input features, but at the end you seems to use only the joints position. Is this somethings i'm...

antho6222

Does this project use the CMU motion data? How cloud I get the training motion data from cmu data?

1

As above.

hellozjj