This repo is forked from https://github.com/marlbenchmark/on-policy for training on the Werewolf game.

Installation

Here we give an example installation on CUDA == 10.1. For non-GPU & other CUDA version installation, please refer to the PyTorch website. We remark that this repo. does not depend on a specific CUDA version, feel free to use any CUDA version suitable on your own computer.

# create conda environment
conda create -n marl python==3.6.1
conda activate marl
pip install torch==1.5.1+cu101 torchvision==0.6.1+cu101 -f https://download.pytorch.org/whl/torch_stable.html

# install on-policy package
cd on-policy
pip install -e .

Even though we provide requirement.txt, it may have redundancy. We recommend that the user try to install other required packages by running the code and finding which required package hasn't installed yet.

Train

Here we use train_mpe.sh as an example:

cd onpolicy/scripts
chmod +x ./train_mpe.sh
./train_mpe.sh

Local results are stored in subfold scripts/results. Note that we use Weights & Bias as the default visualization platform; to use Weights & Bias, please register and login to the platform first. More instructions for using Weights&Bias can be found in the official documentation. Adding the --use_wandb in command line or in the .sh file will use Tensorboard instead of Weights & Biases.