DeepMimic
DeepMimic copied to clipboard
xbpeng
Motion imitation with deep reinforcement learning.
Excuse me, I met some problems about glutInit error. When I run the DeepMimic.py, The following will occur: Traceback (most recent call last): File "DeepMimic.py", line 319, in main() File...
Is it possible to load .vtp files or other type of geometry files directly from the high-level txt? Otherwise, what is the advised pipeline to follow to modify the core?...
Hi! I am currently working on windows 10 (64 bit) and am not able to install mesa and its utilities. I presume that mesa is primarily used for visualization purposes....
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...
I have tried #82 and make sure it's not the problem about USE_DOUBLE_PERCISION. In fact, before I met this problem I was able to run the DeepMimic.py and mpi_run.py. I...
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...
I would like to Train the agent capable to turn left, right, go forward. as in the published video [https://youtu.be/vppFvq2quQ0?t=332](https://youtu.be/vppFvq2quQ0?t=332)... Please let me know how to do it. and is...
Hi, I have tried to implement the Multi-Clip reward technique, but so far I have not achieved great results. My goal is to reproduce the steering behavior shown in the...
is there any way to make the training stop after N samples/iterations?
Hello everyone, when I ran `python mpi_run.py --arg_file args/train_humanoid3d_spinkick_args.txt --num_workers 4` to train the agent as the introduction says, there was error like ``` Running with 4 workers cmd: mpiexec...
