Research / Tags / lemario

Tagged: lemario

1 post tagged lemario.

• A JEPA world model that learns Mario by playing itself Fifteen closed-loop iterations, a 3σ false positive, and what we're rebuilding before iter 16. May 25, 2026 · ~20-minute read We trained a self-supervised JEPA world model on NES Super Mario Bros and ran a closed-loop flywheel — collect, retrain the world model, train a policy in imagination, repeat — for fifteen iterations. The headline iter looked like a breakthrough; a five-seed re-run revealed it was a draw from a much wider distribution than we'd been measuring. This is the project so far, and the redesign that comes next.
  • research notes
  • lemario
  • world models
  • reinforcement learning
  • game playing ai

← All tags