Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/YuriCat/TamakEriFever
AI for google research football
https://github.com/YuriCat/TamakEriFever
Last synced: about 2 months ago
JSON representation
AI for google research football
- Host: GitHub
- URL: https://github.com/YuriCat/TamakEriFever
- Owner: YuriCat
- Created: 2020-12-10T14:07:03.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2020-12-14T11:08:27.000Z (almost 4 years ago)
- Last Synced: 2024-05-22T04:32:30.604Z (4 months ago)
- Language: Python
- Size: 3.84 MB
- Stars: 26
- Watchers: 4
- Forks: 9
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# TamakEriFever: Google Research Football AI Engine
[kaggle competition](https://www.kaggle.com/c/google-football/)
# Usage
## Build docker image
```bash
docker build -t football:latest -f Dockerfile .
```## Run docker container
```bash
docker run --ipc host --name football -v $PWD:/home -w=/ --rm -it football:latest /bin/bash -c "cd /home && /bin/bash"
```## Rendering game vs builtin_ai
```bash
python view_test.py
```## Evaluation vs several agents
```bash
python handyrl.py --eval ${MODEL_PATH} ${NUM_GAMES} ${NUM_WORKERS}
```## Training
### Server machine
```bash
OMP_NUM_THREADS=1 python handyrl.py --train-server
```### Worker machines
```bash
python handyrl.py --worker
```