Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development
Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development
The Game2Player framework, through collaborative development of game environments and players, collects large-scale diverse and verifiable game experiences, including 568 verified web games and 3,436 tasks, collecting 15.7K trajectories (307 hours of game data), building the PlayerBench benchmark.
Published on Nov 18
Authors:
,
,
,
,
,
,
,
,
,
,
,
Abstract
Games are a rich testbed for visual agents, demanding perception, long-horizon planning, and precise control. However, collecting human gameplay is costly, and learning from gameplay videos requires inferring missing actions. Existing datasets also cover a limited range of games, often without explicit tasks or verifiable outcomes. To address these gaps, we introduce Game2Player, a framework that co-develops game environments and players to collect diverse and verifiable gameplay experience at scale. In the Game2Player loop, a Builder agent adapts existing web games, exposes their internal state, and defines tasks with state-based progress measures and success checks. A Coding Player and a VLM Player then attempt the tasks and report problems to the Builder for repair, so that play serves as both environment validation and training data collection. With Game2Player, we build 568 verified web games with 3,436 tasks, collect 15.7K trajectories (307 hours of gameplay), and hold out 50 games as the benchmark PlayerBench. To evaluate the collected experience as training data, we train VLM agents with progress-weighted SFT, assigning greater weight to steps that advance task progress. Game2Player-9B improves progress from 14.3% to 31.2% on PlayerBench and from 30.0% to 53.1% on the external GameWorld benchmark. More broadly, our work suggests a path for visual agents to scale their gameplay experience by building, verifying, and learning from existing game worlds.
View arXiv page View PDF Project page GitHub 21 Add to collection
Models citing this paper 2
Image-Text-to-Text • 9B • Updated about 7 hours ago • 126 • 3game2player/Game2Player-9B
Image-Text-to-Text • 5B • Updated about 7 hours ago • 112 • 1game2player/Game2Player-4B
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.24154 in a dataset README.md to link it from this page.
Spaces citing this paper 1
Collections including this paper 1
Source: Hugging Face Daily Papers · huggingface.co