This is a simple implementation of DeepMind's PySC2 RL agents.
This is a simple implementation of DeepMind's PySC2 RL agents. In this project, the agents are defined according to the original paper, which use all feature maps and structured information to predict both actions and arguments via an A3C algorithm.
pip install s2clientprotocol==1.1
pip install pysc2==1.1
pip
is set up on your system, it can be easily installed by runningpip install absl-py
pip install tensorflow-gpu
Clone this repo:
git clone https://github.com/xhujoy/pysc2-agents
cd pysc2-agents
Download the pretrained model from here and extract them to ./snapshot/
.
Test the pretrained model:
python -m main --map=MoveToBeacon --training=False
MoveToBeacon | CollectMineralShards | DefeatRoaches | |
Mean Score | ~25 | ~62 | ~87 |
Max Score | 31 | 97 | 371 |
Train a model by yourself:
python -m main --map=MoveToBeacon
Licensed under The MIT License.