MIRA – Multiplayer World Model Trained on Rocket League

Join the discussion

• Hacker News
• Is this now the easiest way to play Rocket League on Linux?
  by LorenDB
• The checkpoint also weights half less than the game install! ;-)
  by MasterScrat
• it would have been easier to just go to FNAC and buy Rocket League like a normal person :)
  by _willmanning
• you should do that too! the goal is not to replace the game but to foster research on these method, and hopefully apply them to data-constrained settings like robotics
  by cataPhil
• Nice to know my inability to play Rocket League with any level of skill carries over to this world model
  by ggarnhart
• this is insane - what’s your thinking on how this improves model grounding and efficiency vs single pov outputs?
  by exortaz
• A lot actually, since the model has all information given to it in the four views, it doesn't have to deal with any "theory of mind" of modeling the other players or being consistent over long times. See [1], there's a video of a single-player model where a car disappears behind a ball and never reappears. Multiplayer has its own risks such as the four views desynchronizing, but overall it gives a big boost to the model.

  [1] https://mira-wm.com/blog-post/#hidden-information

  by vvolhejn
• We're happy to release MIRA, a collaboration between General Intuition, Kyutai, and Epic Games.

  Mira was trained on 10k hours of Rocket League data. The model has 5B parameters and runs 4-player games at 20 fps on a single B200 GPU.

  We've released a playable online demo, an in-depth technical report as well as a 1k hour dataset of 4-players gameplay:

  Technical report: https://mira-wm.com/paper Repo: https://github.com/mira-wm/mira

  by MasterScrat
• How much compute did it take to train the model?
  by lostmsu
• Václav here from the team, we're happy to answer questions :) The most surprising part to me is the auto-recovery behavior we mention at the end of the blog post, since any other model I've seen always stays diverged once it goes off the rails once. But MIRA really doesn't like to be out-of-distribution. To be completely honest we're not entirely sure why this happens.
  by vvolhejn
• Great work! My question is about what you mentioned at the end - how well do world models operate when out of distribution? In some sense we hope these models learn something "deeper" about how the world works and can apply that knowledge to different tasks.

  I saw lots of awesome ablations in the paper (loved it!), but I'm curious if you analyzed the latents to get an intuition for what the model actually learned. Or, is it just that it learned the training data distribution really, really well?

  by shay_ker
• Wow! At first, I expected this to be a demonstration of an AI playing rocket league, but I rapidly realized this is actually a model simulating rocket league. Wild! It feels just like the real game.
  by danking00