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.
Install on Linux
git clone [email protected]: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
Install on OSX
Note: There is an issue with homebrew for installing websocketpp, please refer to #17
git clone [email protected]:geek-ai/MAgent.git cd MAgent brew install cmake llvm boost brew install jsoncpp argp-standalone brew tap david-icracked/homebrew-websocketpp brew install --HEAD david-icracked/websocketpp/websocketpp bash build.sh export PYTHONPATH=$(pwd)/python:$PYTHONPATH
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
Three examples shown in the above video. Video files will be saved every 10 rounds. You can use render to watch them.
python examples/train_pursuit.py --train
python examples/train_gather.py --train
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
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.