AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

End-to-End Game-Focused Learning of Adversary Behavior in Security Games

Andrew Perrault, Bryan Wilder, Eric Ewing, Aditya Mate, Bistra Dilkina, Milind Tambe

AAAI 2020 · Learning theory and algorithms › Submodular and game algorithms · approach: Opponent modeling and subgame solving · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train adversary model end-to-end on defender expected utility instead of two-stage prediction accuracyGF · Synthetic SSG (8 and 24 targets)defender expected utilityImproved
game-focused vs two-stage on human subject data, 8 targetsGF · Nguyen et al. human dataDEU: 28% more DEU than 2S-GT at 5 attacksImproved
game-focused vs two-stage on human subject data, 24 targetsGF · Nguyen et al. human dataDEU: 66% more DEU than 2S at 1 attackImproved
more training data or fewer features (easier learning)GF vs 2S-GT · Synthetic SSGDEU gapHurt
GF vs 2S-GT on prediction qualityGF · Human subject datatest cross entropy: 2-20% higher cross entropyHurt
tune two-stage model for small data (2S-GT vs 2S)two-stage · Synthetic SSGDEUImproved
GF with less model uncertainty (lower 2S cross entropy)GF · Synthetic SSGDEU gap vs 2SImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy