---
title: "多玩家交互世界模型：基于表示自编码器的多人动态环境建模"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.05352v1"
permalink: "https://feed.astralor.com/items/itm_ced280b2e02fb06dbde96de1"
published: "2026-07-06T17:31:52.000Z"
score: 81
channel: "ai"
tags: ["Nvidia B200","Rocket League","世界模型","多智能体系统","潜在扩散模型","表示自编码器"]
---

# 多玩家交互世界模型：基于表示自编码器的多人动态环境建模

## AI 点评

> 这篇论文值得所有从事世界模型、多智能体强化学习和游戏AI的开发者关注。它解决了世界模型最实际的限制——无法处理多个主动智能体的交互。50亿参数在单卡上跑20fps，加上数小时稳定性，说明架构和优化相当扎实。虽然目前只测试了Rocket League，但方法有希望迁移到其他物理模拟场景。开源的1万小时数据集和代码库将极大降低后续研究门槛。

## 速览

本文提出了首个面向高度动态、复杂物理交互环境的多人世界模型。不同于单玩家世界模型将其他智能体视为环境的一部分，该模型基于多个智能体的动作流进行条件生成，学习将场景变化归因于正确的玩家，并在任意动作组合下保持一致性。研究在《火箭联盟》游戏中展开，训练于1万小时公开机器人游戏数据，构建了50亿参数的潜在扩散模型，能在单张Nvidia B200 GPU上实时生成4玩家比赛（每秒20帧）。尽管仅用短片段训练，模型滚动稳定性远超训练视野：分布质量在5分钟内保持稳定，实践中可延续数小时而不崩溃。系统研究了视频编解码器、生成目标和多人条件方案等核心设计选择，并表征了模型和数据规模对行为的影响，包括涌现能力与失败模式。论文还开发了针对性评估以探测模型对物理的理解，并开放了数据集、完整训练/推理代码和在线演示。

## 关键点

- 首个针对多智能体、高动态物理环境的交互世界模型，将多个玩家的动作流作为条件。
- 模型架构：50亿参数潜在扩散模型，在《火箭联盟》1万小时数据上训练，实时生成4玩家比赛（20 FPS / B200 GPU）。
- 稳定性突破：仅用短片段训练，但滚动可持续数小时不崩溃，分布质量在5分钟测试窗口内保持稳定。
- 开源贡献：发布数据集、完整训练/推理代码和在线演示，促进多人世界模型研究。

## 全文

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, our 5-billion-parameter latent diffusion model generates four-player matches in real time, producing 20 frames per second on a single Nvidia B200 GPU. Although trained only on short clips, its rollouts stay stable far beyond the training horizon: distributional quality holds steady out to five minutes, the longest horizon we measure, and in practice we observe rollouts continuing for hours with no sign of collapse. We systematically investigate the central design choices: the video codec, the generative objective, and the multiplayer conditioning scheme. In addition, we characterize how behavior changes with model and data scale, including the capabilities that emerge and the failure modes that persist. We further develop targeted evaluations that probe the model's physical understanding rather than visual appearance alone. To support continued research on multiplayer world models, we release our dataset, our full training and inference codebase, and a live demo.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_ced280b2e02fb06dbde96de1