lyu-xg/RODE

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.

RODE: Learning Roles to Decompose Multi-Agent Tasks

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.

This implementation is written in PyTorch and is based on PyMARL and SMAC.

Installation instructions

Build the Dockerfile using

cd docker
bash build.sh

Set up StarCraft II and SMAC:

bash install_sc2.sh

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).

Run an experiment

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 epsilon_anneal_time_exp.

All results will be stored in the Results folder.

Saving and loading learnt models

Saving models

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.

Loading models

Learnt models can be loaded using the checkpoint_path parameter, after which the learning will proceed from the corresponding timestep.

Watching StarCraft II replays

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.