repoGitLabTrust 82 · PrimaryPublished 12d agoLive · 12d ago
ar39907/video-game-machine-learning
Black-box bot that plays Super Mario Bros (NES) via screen-pixel reading and simulated keypresses; no game-memory access, no trained model.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%Fun Game - https://numdle-game.pages.dev/ [P] →
- PossiblePossibly related (embedding) · 48%LeMario: Training a JEPA World Model on Super Mario Bros →
- PossiblePossibly related (embedding) · 48%Generative AI and Game Art Statistics (2026) - Shane the Gamer →
- PossiblePossibly related (embedding) · 48%TechCrunch Disrupt 2026’s new Real World AI Stage features Nvidia, robots, and extinct animals →
Covers
Covers (incoming)
Related across the graph
newsTechCrunch Disrupt 2026’s new Real World AI Stage features Nvidia, robots, and extinct animalsnewsFun Game - https://numdle-game.pages.dev/ [P]newsGoogle maps entire brain and central nervous system of adult male fruit fly, software engineers immediately make it run Doom — AI-powered 3D model of over 166,000 neurons can also play Super Mario 64 - Tom's HardwarenewsLeMario: Training a JEPA World Model on Super Mario BrosnewsGenerative AI and Game Art Statistics (2026) - Shane the Gamer