Multiplayer Interactive World Models with Representation Autoencoders

• URL: http://arxiv.org/abs/2607.05352v2
• Date: Tue, 07 Jul 2026 16:09:47 GMT
• Title: Multiplayer Interactive World Models with Representation Autoencoders
• Abstract summary: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions.<n>We study this problem in the game of Rocket League, where players compete and cooperate under fast, tightly coupled dynamics.
• Score: 28.451678067070777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives [86.3073067035531]
  Video world models simulate future states conditioned on current observations and user actions.<n>Recent systems have demonstrated impressive video consistency and action controllability over long sequences.<n>But fairly comparing these interactive models remains challenging.<n>We employ multi-modal Agent Players to interact with world models toward specified long-horizon objectives.
  arXiv  Detail & Related papers  (2026-08-13T17:59:30Z)
• Infinite Worlds with Versatile Interactions [72.56254206708059]
  LingBot-World 2.0 (also known as LingBot-World-Infinity) is an advanced iteration of LingBot-World.<n>This update introduces highly diverse interactive elements, comprising a broader spectrum of actions.<n>To facilitate a shared experience, we develop an interface that permits multiple players to simultaneously immerse themselves in this vivid world simulator.
  arXiv  Detail & Related papers  (2026-07-08T15:33:25Z)
• EgoCS-400K: An Egocentric Gameplay Dataset for World Models [53.9389499966106]
  We introduce EgoCS-400K, a large-scale replay-grounded egocentric Counter-Strike dataset for world models.<n>It is built from public professional CS and CS2 match demos that preserve human gameplay trajectories.<n>EgoCS-400K contains over 400,000 first-person videos and 10,000 hours of gameplay from more than 1,000 matches and 40,000 rounds.
  arXiv  Detail & Related papers  (2026-06-16T17:13:58Z)
• ActionParty: Multi-Subject Action Binding in Generative Video Games [117.52562594944679]
  ActionParty is a controllable multi-subject world model for generative video games.<n>We demonstrate the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments.
  arXiv  Detail & Related papers  (2026-04-02T17:59:58Z)
• Solaris: Building a Multiplayer Video World Model in Minecraft [25.935990718354176]
  Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives.<n>We introduce Solaris, a multiplayer video world model that simulates consistent multi-view observations.<n>We collect 12.64 million multiplayer frames and propose an evaluation framework for multiplayer movement, memory, grounding, building, and view consistency.
  arXiv  Detail & Related papers  (2026-02-25T18:59:01Z)
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos [110.98100817695307]
  We introduce DreamDojo, a foundation world model that learns diverse interactions and dexterous controls from 44k hours of egocentric human videos.<n>Our work enables several important applications based on generative world models, including live teleoperation, policy evaluation, and model-based planning.
  arXiv  Detail & Related papers  (2026-02-06T18:49:43Z)
• NitroGen: An Open Foundation Model for Generalist Gaming Agents [101.41866522979548]
  NitroGen is a vision-action foundation model for generalist gaming agents.<n>It is trained on 40,000 hours of gameplay videos across more than 1,000 games.
  arXiv  Detail & Related papers  (2026-01-04T16:24:50Z)
• Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model [15.16063778402193]
  Matrix-Game 2.0 is an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion.<n>It can generate high-quality minute-level videos across diverse scenes at an ultra-fast speed of 25 FPS.
  arXiv  Detail & Related papers  (2025-08-18T15:28:53Z)
• MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft [21.530000271719803]
  We propose MineWorld, a real-time interactive world model on Minecraft.<n>MineWorld is driven by a visual-action autoregressive Transformer, which takes paired game scenes and corresponding actions as input.<n>We develop a novel parallel decoding algorithm that predicts the spatial redundant tokens in each frame at the same time.
  arXiv  Detail & Related papers  (2025-04-11T09:41:04Z)
• From Motor Control to Team Play in Simulated Humanoid Football [56.86144022071756]
  We train teams of physically simulated humanoid avatars to play football in a realistic virtual environment. In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements. They then acquire mid-level football skills such as dribbling and shooting. Finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds.
  arXiv  Detail & Related papers  (2021-05-25T20:17:10Z)
• Mastering Atari with Discrete World Models [61.7688353335468]
  We introduce DreamerV2, a reinforcement learning agent that learns behaviors purely from predictions in the compact latent space of a powerful world model. DreamerV2 constitutes the first agent that achieves human-level performance on the Atari benchmark of 55 tasks by learning behaviors inside a separately trained world model.
  arXiv  Detail & Related papers  (2020-10-05T17:52:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.