A machine learning project using DeepMind's PySC2 and Tensorflow.
I refered to Sunghun Kim's repository for DQN class, etc.
At first, please download my git and some prerequisites.
Here's my example.
git clone https://github.com/phraust1612/MinervaSc2.git
sudo pip3 install pysc2
sudo pip3 install numpy
sudo pip3 install tensorflow
Specify your saving directory. For default, DQN structure will be saved at 'saved/',
so be sure that 'saved/' directory exists or prepare for your own.
python3 trainingRL.py --start_episode (##) --num_episodes (##)
For default, starting episode and total number would be 0 and 100
python3 trainingSL.py --replay (your replay directory) --repeat (no of repetition)
For default option, this will refer ~/StarCraftII/Replays/ for replay files
- trainingRL.py : run reinforcement learning loops via DQN.
- trainingSL.py : run supervised learning loops with your replay files.
- minerva_agent.py : contains an agent class which decides actions for every step.
- dqn.py : DQN network class, in order to devide target and learning networks.