Please see https://github.com/Farama-Foundation/MAgent2 for a maintained fork of this project that's installable with pip.

MAgent is a research platform for many-agent reinforcement learning. Unlike previous research platforms that focus on reinforcement learning research with a single agent or only few agents, MAgent aims at supporting reinforcement learning research that scales up from hundreds to millions of agents.

• AAAI 2018 demo paper: MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
• Watch our demo video for some interesting show cases.
• Here are two immediate demo for the battle case.

MAgent supports Linux and OS X running Python 2.7 or python 3. We make no assumptions about the structure of your agents. You can write rule-based algorithms or use deep learning frameworks.

git clone git@github.com:geek-ai/MAgent.git
cd MAgent
sudo apt-get install cmake libboost-system-dev libjsoncpp-dev libwebsocketpp-dev
bash build.sh
export PYTHONPATH=$(pwd)/python:$PYTHONPATH

Note: There is an issue with homebrew for installing websocketpp, please refer to #17

git clone git@github.com:geek-ai/MAgent.git
cd MAgent
brew install cmake llvm boost@1.55
brew install jsoncpp argp-standalone
brew tap david-icracked/homebrew-websocketpp
brew install --HEAD david-icracked/websocketpp/websocketpp
brew link --force boost@1.55
bash build.sh
export PYTHONPATH=$(pwd)/python:$PYTHONPATH

Get started

The training time of following tasks is about 1 day on a GTX1080-Ti card. If out-of-memory errors occur, you can tune infer_batch_size smaller in models.

Note : You should run following examples in the root directory of this repo. Do not cd to examples/.

Three examples shown in the above video. Video files will be saved every 10 rounds. You can use render to watch them.

• pursuit

   python examples/train_pursuit.py --train
  

• gathering

   python examples/train_gather.py --train
  

• battle

   python examples/train_battle.py --train
  

An interactive game to play with battle agents. You will act as a general and dispatch your soldiers.

• battle game

  python examples/show_battle_game.py
  

The baseline algorithms parameter-sharing DQN, DRQN, a2c are implemented in Tensorflow and MXNet. DQN performs best in our large number sharing and gridworld settings.

Many thanks to Tianqi Chen for the helpful suggestions.