KeWang

Hi I followed the instructions and trained the act policy for relatively long time (around 6 hours and 50k steps) and the success rate does not seem to be great....

Hi after realizing that data generated by script is mostly fail #12 , i use the demo data provided by the author. However I ran into data loading error when...

Hi when I want to record videos by running the command `train.py \ task=HumanoidAMP \ experiment=AMP_walk \ capture_video=True \ force_render=True \` and it gives me the erro `TypeError: render() got...

Segmentation fault (core dumped) when running examples

1

Hi I am trying to use C-Frost for the newest version, all the installation and compilation worked fine. But on both examples (NLP and Rabbit), when I follow the instruction...

Self Collisions

2

Hi, When we test our trained policy for uneven terrain we find the legs are crossing each other when we command the robot to turn around. Then we realize that...

## What this does 1. Solve the nan issue of action log probability by using a numerically more stable temperature computation. 2. Solve the un-converged actor&critic loss by adding `torch.inference_mode`...

## What this does The current `reset_environment()` function enables teleoperation but removes the progress bar. Rewrite the `reset_enviornmnet()` with progress bar but it also creates some replicate code. ## How...