MIRA: Multiplayer Interactive World Models Trained on Rocket League

in-silico 25 minutes ago | parent | next [-]

I feel like the data should have been generated by a much less predictable policy.

It often feels like the model is ignoring my inputs and just doing what it would expect the bot to do (which is unsurprising if the model could predict what would happen next during training without paying attention to the inputs)

▲

jorl17 3 hours ago | parent | prev | next [-]

This was a much better experience than I expected. Rather unbelievable!

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!

▲

MasterScrat 2 hours ago | parent | prev | next [-]

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. Instead it’s a 5b neural network that takes actions in and gives pixels out.

	▲	pvillano 26 minutes ago \| parent \| next [-]
		Could a network be trained to transform physics state directly into the latent state and back? 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.
	▲	pizzathyme an hour ago \| parent \| prev [-]
		Tim Sweeney’s interviews on the uses of GenAI for game development have been some of the best takes I’ve heard. He’s mentioned how GenAI is great at filling in the gaps or treating assets, but no world simulation means no deep persistence or authoring for a whole new unique game world. What is the conversation like within Epic now? Is this still the view? What is the future for simulations like this?

▲

bschwindHN 2 hours ago | parent | prev | next [-]

Where is the option to call all of my tm8s trash? That's an essential part of the experience!

	▲	MitziMoto 23 minutes ago \| parent [-]
		What a save! What a save! What a save! (Chat disabled for 3s)

▲

avaer 2 hours ago | parent | prev | next [-]

If the data and code is all there, why not release the 5B weights?

▲

superkuh 2 hours ago | parent | prev [-]

It feels like playing on a very slow computer. Except that sometimes it just randomly decides you pressed the flip button. Really impressive.