MIRA: A Real-Time AI Simulation of Four-Player Rocket League
MIRA: Multiplayer Interactive World Models Trained on Rocket League
I present MIRA, a groundbreaking multiplayer world model trained on 10,000 hours of Rocket League gameplay using publicly available bots. This system learns the complex dynamics of a four-player game and runs in real time at 20fps, responding directly to the keys you and other players press. While this simulation offers a dream-like experience, it cannot replace the thrill of the official Rocket League game.
Of course, a simulation cannot replace the real thing.
- amarant
Pretty insane that you can get this close to the real thing this way.
Rocket league is one of my favourite games, and I'm pretty decent at it (rank champion 1). I kinda felt like my controller was a bit broken when playing this, a lot of commands were just ignored, and forget doing stuff like speed flips. But I did feel like was controlling the car, and everything about the game looked very much like the real thing. Ball movement was on point, I didn't notice any weird bounces or anything.
The lack of opponents pulling triple flip resets and double-tapping musty's (musties?) was the most notable difference from the real thing
- jorl17
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!
- danking00
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.
- superkuh
It feels like playing on a very slow computer. Except that sometimes it just randomly decides you pressed the flip button. Really impressive.
- vvolhejn
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.