LeMario: Super Mario Bros trained on a JEPA Model
- I wanted to reproduce LeWorldModel, a small Joint-Embedding Predictive Architecture (JEPA) that learns world dynamics from pixels and actions.
- The original paper used it for reward-free planning in Push-T.
- But, since I loved video games, and at the same time wanted to learn more deeply about LeCun's JEPA architecture, I decided to write the whole architecture from scratch and train it on Super Mario Bros.
Unverified
- I wanted to reproduce LeWorldModel, a small Joint-Embedding Predictive Architecture (JEPA) that learns world dynamics from pixels and actions.
- The original paper used it for reward-free planning in Push-T.
- But, since I loved video games, and at the same time wanted to learn more deeply about LeCun's JEPA architecture, I decided to write the whole architecture from scratch and train it on Super Mario Bros.
Sources: Benjamin-bai