055-amp-adversarial-motion-priors-for-stylized-physics-based-character-control

https://github.com/szu-advtech-2023/055-amp-adversarial-motion-priors-for-stylized-physics-based-character-control

Science Score: 18.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (3.3%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: SZU-AdvTech-2023
Default Branch: main
Size: 0 Bytes

Statistics

Stars: 0
Watchers: 0
Forks: 0
Open Issues: 0
Releases: 0

Created over 2 years ago · Last pushed over 2 years ago

Metadata Files

Citation

https://github.com/SZU-AdvTech-2023/055-AMP-Adversarial-Motion-Priors-for-Stylized-Physics-Based-Character-Control/blob/main/

## AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control

### 

 Linux Python 3.8 3D

 Isaac Gym Preview 4 [](https://developer.nvidia.com/isaac-gym)`python/examples` `joint_monkey.py`



```
"gym==0.23.1",
"torch",
"omegaconf",
"termcolor",
"jinja2",
"hydra-core>=1.2",
"rl-games>=1.6.0",
"pyvirtualdisplay",
"urdfpy==0.0.22",
"pysdf==0.1.9",
"warp-lang==0.10.1",
"trimesh==3.23.5",
```

### 

 HumanoidAMPPO.yaml  `reward_combine: 'add' ` 

```bash
python launch.py task=HumanoidAMP headless=True
```



```bash
python launch.py task=HumanoidAMP headless=False test=True num_envs=64 checkpoint=/path/to/saved/model/in/runs/nn
```

 HumanoidAMPPO.yaml  `reward_combine: 'mul' ` 

```bash
python launch.py task=HumanoidAMP headless=True
```



```bash
python launch.py task=HumanoidAMP headless=False test=True num_envs=64 checkpoint=/path/to/saved/model/in/runs/nn
```

### 



```bash
python launch.py task=HumanoidAMP headless=False test=True num_envs=64 checkpoint=/path/to/saved/model/in/runs/nn capture_video=True
```



### 

 `fmbvh` 

`./isaacgymenvs/tasks/amp/utils_amp/motion_lib.export_bvh`

`./runs/`

Owner

Name: SZU-AdvTech-2023
Login: SZU-AdvTech-2023
Kind: organization

Repositories: 1
Profile: https://github.com/SZU-AdvTech-2023

Citation (citation.txt)

@article{REPO055,
    author = "Peng, Xue Bin and Ma, Ze and Abbeel, Pieter and Levine, Sergey and Kanazawa, Angjoo",
    journal = "ACM Transactions on Graphics (ToG)",
    number = "4",
    pages = "1--20",
    title = "{AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control}",
    volume = "40",
    year = "2021"
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science