Multiplayer Interactive World Models with Representation Autoencoders
We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents as part of the environment, ours conditions on the action streams of multiple agents, learning to attribute changes in the scene to the correct player and to stay coherent under arbitrary combinations of their actions. We study this problem in the game of Rocket League, where players compete and cooperate under fast, tightly coupled dynamics. Trained on 10,000 hours of gameplay collected with publicly available bots,
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%Agentic AI for Robot Teams →
- PossiblePossibly related (embedding) · 53%grandgaming9321-prog/reality-engine →
- PossiblePossibly related (embedding) · 50%ahumblenerd/tour-of-agents →
- PossiblePossibly related (embedding) · 50%2FastLabs/agent-squad →
- PossiblePossibly related (embedding) · 50%xlang-ai/OSWorld →
- LinkedLinked via arxiv author · 85%Anthony Hu →
“Multiplayer Interactive World Models with Representation Autoencoders”
- LinkedLinked via arxiv author · 85%Václav Volhejn →
“Multiplayer Interactive World Models with Representation Autoencoders”
- LinkedLinked via arxiv author · 85%Adrien Ramanana Rahary →
“Multiplayer Interactive World Models with Representation Autoencoders”