Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
End-to-End Game-Focused Learning of Adversary Behavior in Security Games
Authors: Andrew Perrault, Bryan Wilder, Eric Ewing, Aditya Mate, Bistra Dilkina, Milind Tambe1378-1386
AAAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We test our approach on a combination of synthetic and human subject data and show that game-focused learning outperforms a two-stage approach in settings where the amount of data available is small and when there is wide variation in the adversary s values for the targets. |
| Researcher Affiliation | Academia | 1Center for Research on Computation and Society, Harvard 2Center for Artificial Intelligence in Society, University of Southern California |
| Pseudocode | No | The paper describes its approach and flow with diagrams but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement about releasing source code or providing a link to it. |
| Open Datasets | Yes | We use data from human subject experiments performed by Nguyen et al. (2013). |
| Dataset Splits | Yes | Game-tuned two-stage (2S-GT) is a regularized approach that aims to maximize the defender s expected utility when the amount of data is small. It uses Dropout (Srivastava et al. 2014) and a validation set for early stopping. |
| Hardware Specification | No | The paper does not specify any hardware details such as GPU/CPU models, memory, or specific computing environments used for experiments. |
| Software Dependencies | No | The paper mentions implementing neural networks and using gradient descent, but does not provide specific software dependencies or version numbers (e.g., Python, TensorFlow, PyTorch versions). |
| Experiment Setup | Yes | Unless it is varied in an experiment, the parameters are: 1. Number of targets = |T | {8, 24}. 2. Features per target = |y|/|T | = 100. 3. Number of training games = |Dtrain| = 50. ... 6. We fix the attacker s weight on defender coverage to be w = 4 (see Eq. 2)... |