Hasty Briefsbeta

Bilingual

Teaching a World Model to Play Pokemon

6 hours ago
  • The author trained a JEPA-based world model (LeWorldModel) on Pokémon Red screenshots to plan button sequences for selecting a starter Pokémon.
  • World models learn state-transition dynamics from observations without rewards; the model predicts future embeddings rather than raw screenshots.
  • To prevent latent collapse (all embeddings becoming identical), SIGReg regularization encourages embeddings to resemble an isotropic Gaussian.
  • Training data consisted of 42,382 grayscale frames grouped into 1,009 short trajectories, including both clean and noisy routes.
  • Planning uses predicted embeddings from a 14-step rollout and the cross-entropy method (CEM) to search for sequences that minimize distance to goal embeddings.
  • Initial plans failed due to compounding prediction errors; rollout fine-tuning (training the predictor on its own predictions) improved performance.
  • After fine-tuning, the model achieved 52% success rate in selecting a starter (Squirtle) from a saved state in Oak's Lab, compared to 0% for random actions.
  • The final model had ~12.5 million parameters, trained end-to-end from scratch, and remained limited to short tasks due to exponential difficulty scaling.