Spaces:
Running
Running
| title: README | |
| emoji: ⚡ | |
| colorFrom: red | |
| colorTo: yellow | |
| sdk: static | |
| pinned: false | |
| # 🎮 Game2Player | |
| **Scaling Gameplay Experience for Visual Agents through Environment–Player Co-Development** | |
| [🌐 Project Website](https://game2player.github.io/) · [💻 GitHub](https://github.com/game2player/Game2Player) · [🤗 Collection](https://huggingface.co/collections/game2player/game2player-project) | |
| Game2Player explores how visual agents learn to play games through environment–player co-development. We bring together game environments, gameplay experience, and trained players to study visual decision-making and interactive control. | |
| Our models take game screenshots, task instructions, and recent actions as input, then predict the next keyboard or mouse action. | |
| ## 🤖 Models | |
| Explore our visual game-playing models, with weights and usage instructions available in each repository: | |
| - [**Game2Player-4B**](https://huggingface.co/game2player/Game2Player-4B) | |
| - [**Game2Player-9B**](https://huggingface.co/game2player/Game2Player-9B) | |
| ## 🏆 Evaluation | |
| We evaluate visual agents on **PlayerBench**, featuring **50 held-out games and 287 tasks**, and **GameWorld**, featuring **34 games and 170 tasks**. | |
| [Explore PlayerBench](https://github.com/game2player/Game2Player/tree/main/benchmark/playerbench) · [View the Leaderboard](https://game2player.github.io/#leaderboard) | |
| ## 🚀 Get Started | |
| Visit our [GitHub repository](https://github.com/game2player/Game2Player) for code and benchmark instructions, or open a model card to run a Game2Player model. | |
| Questions, feedback, and contributions are welcome through [GitHub Issues](https://github.com/game2player/Game2Player/issues). |