A link to our paper can be found on Arxiv.
Official codebase for Offline Pre-trained Multi-Agent Decision Transformer. Contains scripts to reproduce experiments.
It may be necessary to add the respective directories to your PYTHONPATH.
The offline smac dataset for this repo is available at here, expired.
## password is xvsma7
New download link [here](https://cowtransfer.com/s/3785a6a9e5d044)
- setup python environment with
pip install -r requirements.txt
- to install StarCraft II & SMAC, you could run
bash install_sc2.sh
. Or you could install them manually to other path you like, following the official link: https://github.com/oxwhirl/smac. - enter the
./sc2/
folder. - set hyper-parameters in
run_madt_sc2.py
line 19-49 according to appendix. - select a maps to test in
envs/config.py
line 142 - run the
run_madt_sc2.py
script
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113^C
pip install -r requirements.txt
pip install pyOpenSSL --upgrade
pip install --upgrade pip
python3 run_madt_sc2.py
python3 run_madt_sc2.py --offline_epochs 1
python3 run_madt_sc2.py --offline_epochs 10
python3 run_rware.py
python3 run_rware.py --eval_episodes 1
python3 run_rware.py --eval_episodes 32
python3 run_robot_warehouse.py