It's the pytorch implementation of google research football.
This is the pytorch example of the google football research, more contents will be updated soon!:soccer:
Please install the gfootball
according to the instructions here.
pip
is less than 19
, the lastest version of pip
will disable --process-dependency-links
.conda install pip==18.1
gfootball
).pip install tensorflow
git clone https://github.com/google-research/football.git
cd football
pip install .[tf_cpu] --process-dependency-links (we don't need GPU for tensorflow)
Train the simple example - academy_empty_goal_close
python train_example.py --cuda (if you have a GPU)
Play the demo:
python demo.py
academy_empty_goal_close | academy_run_to_score |
---|---|
academy_3_vs_1_with_keeper | academy_counterattack_easy |
---|---|