AI 学会打游戏了，但练它的不是真人，是它自己
现在的 AI 能看懂屏幕、点按钮，但一进游戏就露怯——游戏世界太丰富，动态状态太多，靠人录的演示根本覆盖不过来。这篇的思路是让 AI 自己练：先拿 6 千多条真人操作轨迹做基础，再把它扔进 16 个专门设计的合成游戏环境里，用程序自动判定对错、随机改变画面和操作手感，让它通过强化学习自己摸索。结果在《我的世界》基准测试里，成功率从 12.6% 提到 38.3%，比最强基线翻了三倍。它不是你明天能用上的东西，但这是 AI 从「会操作界面」走向「会玩复杂游戏」的关键一步——练它的不再是有限的真人演示，而是无限的自造经验。
📄 原文摘要(英文)
Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demanding next step toward general digital control. Current game-agent learning pipelines often rely on large-scale demonstrations with limited coverage of dynamic game states, while scalable environments for interactive training remain difficult to obtain. We introduce Player-1, a post-training framework for learning game control beyond demonstrations through synthetic experience. We extend the computer-use action space with relative pointer motion, sustained inputs, and composite actions. For supervised initialization, we fine-tune computer-use models on 6,044 curated gameplay trajectories that pair recorded actions with task instructions and visual reasoning. We construct Player-1-Gym, sixteen synthetic 2D and 3D environments designed around control demands shared across games. Programmatically verifiable rewards and randomized observations and control dynamics support multi-environment reinforcement learning with PPO. The resulting Player-1-9B and Player-1-35B-A3B improve MineDojo-300 success over their SFT policies by 27.8 and 17.7 percentage points, respectively. Player-1-9B reaches 38.33% success compared with 12.63% for the strongest evaluated baseline, with further gains over SFT on ViZDoom-10 and GameWorld. Further analyses show that broader synthetic environment coverage improves transfer, while the use of composite actions that combine multiple keyboard and mouse inputs increases during RL. We demonstrate that learning from synthetic experience substantially improves game control beyond supervised initialization, with gains that generalize beyond the RL training suite.