11–20 of 35 posts
it would have been easier to just go to FNAC and buy Rocket League like a normal person :)
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.co…
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.
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?
Side-effect of the data: clearly the model is better than I normally am at playing, as it spontaneously did several things I had not told it to do and wouldn't really know how to do (at least not with a keyboard).
Really remarkable, congrats!
You can read plenty of details in the blog post and tech report but the TLDR is that we trained a multiplayer world model on 10k hours of Rocket League data. We optimized it to be playable at 20fps on a single GPU.
So what you see in the demo is fully generated: there’s no graphics or physics engine. Instead it’s a 5b neural network that takes actions in and gives pixels out.
Hey all, happy to see this here! This was a colab between General Intuition (that I’m part of), Kyutai and Epic Games. You can read plenty of details in the blog post and tech report but the TLDR is that we trained a multiplayer world model on 10k hours of Rocket League data. We optimized it to be playable at 20fps on a single GPU. So what you see in the demo is fully generated: there’s no graphics or physics engine.…
What is the conversation like within Epic now? Is this still the view? What is the future for simulations like this?
Hey all, happy to see this here! This was a colab between General Intuition (that I’m part of), Kyutai and Epic Games. You can read plenty of details in the blog post and tech report but the TLDR is that we trained a multiplayer world model on 10k hours of Rocket League data. We optimized it to be playable at 20fps on a single GPU. So what you see in the demo is fully generated: there’s no graphics or physics engine.…
Having a direct transformation would enable some interesting experiments.
How is the latent state different when everything else stays the same, but you change one physics value, like player one velocity? Is there a cyclical pattern of activation that correlates strongly with the seconds digit of the clock? Can you decode the latent state, give players full boost, and then re-encode it for infinite boost, without losing continuity?
Edit: There sure are a lot of papers on interpretability.