guaguakai / scalable-game-focused-learning

Implementation of "Scalable Game-Focused Learning of Adversary Models: Data-to-Decisions in Network Security Games" accepted by AAMAS 2020

Scalable Game-Focused Learning

This is the implementation of the work Scalable Game-Focused Learning of Adversary Models: Data-to-Decisions in Network Security Games", Kai Wang, Andrew Perrault, Aditya Mate, and Milind Tambe. in AAMAS 2020

• blockQP.py: the main file which includes the training and data generation. You can simply run ""python3 blockQP.py""
• graphData.py: the file to generate synthetic dataset and other helper functions.
• gcn.py: our learning model graph convolutional network
• derivative.py: all the helper functions responsible for optimization, computing first order derivative, and second order derivative.