README.md

metadata

pipeline_tag: reinforcement-learning
tags:
  - deep
  - reinforcement
  - learning
  - world
  - models

M3: A Modular World Model over Streams of Tokens

📄 Paper ▪️ 💾 Code

🧠 The trained model weights for Atari 100K, DeepMind Control Suite Proprioceptive 500K, and Craftax (Symbolic) 1M.