RODE (ArXiv Link) is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects. It establishes a new state of the art on the StarCraft multi-agent benchmark.
Build the Dockerfile using
cd docker bash build.sh
Set up StarCraft II and SMAC:
This will download SC2 into the 3rdparty folder and copy the maps necessary to run over.
The requirements.txt file can be used to install the necessary packages into a virtual environment (not recomended).
python3 src/main.py --config=rode --env-config=sc2 with env_args.map_name=corridor n_role_clusters=3 role_interval=5 t_max=5050000
To change the annealing time of epsilon, set
All results will be stored in the
You can save the learnt models to disk by setting
save_model = True, which is set to
False by default. The frequency of saving models can be adjusted using
save_model_interval configuration. Models will be saved in the result directory, under the folder called models. The directory corresponding each run will contain models saved throughout the experiment, each within a folder corresponding to the number of timesteps passed since starting the learning process.
Learnt models can be loaded using the
checkpoint_path parameter, after which the learning will proceed from the corresponding timestep.
save_replay option allows saving replays of models which are loaded using
checkpoint_path. Once the model is successfully loaded,
test_nepisode number of episodes are run on the test mode and a .SC2Replay file is saved in the Replay directory of StarCraft II. Please make sure to use the episode runner if you wish to save a replay, i.e.,
runner=episode. The name of the saved replay file starts with the given
env_args.save_replay_prefix (map_name if empty), followed by the current timestamp.
Note: Replays cannot be watched using the Linux version of StarCraft II. Please use either the Mac or Windows version of the StarCraft II client.