AI 打游戏,靠的是看人敲键盘几万小时
一个 AI 想学会打游戏,通常得靠开发者手写规则或专门训练;这篇直接让它看人类敲键盘、点鼠标的原始记录,几万小时,然后它自己就学会了在 3D 开放世界里像熟练玩家一样行动。研究者把「看屏幕、记状态、做决策」装进一个端到端模型,先用海量人机交互数据预训练,再用稀疏思考的指令微调省算力,最后用多轮强化学习解决长任务里的记忆和奖励稀疏问题。它还能在云端同时跑多个游戏环境,延迟低到能实时操作。在多个 3A 大作和 2D 基准上都达到了接近人类玩家的水平。它不是你明天能拿来替你打排位的,但这条「看人操作就能学」的路线,指向的是未来机器人直接看人干活就能学会做事。
📄 原文摘要(英文)
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D graphical interfaces and complex 3D simulated worlds. We first continue pre-training on a dataset constructed from tens of thousands of hours of device-level keyboard and mouse interaction. These trajectories span simulated games and embodied environments, allowing the model to learn environmental dynamics across both physical and virtual domains. Sparse-thinking instruction tuning then substantially reduces redundant computation while preserving the reasoning needed for complex decisions. We train the policy for long-horizon interaction with a stable multi-turn reinforcement learning method that addresses finite context windows, accumulated rollout errors, and sparse rewards. For real-time interaction, a cloud-edge inference engine serves numerous simulated game environments concurrently, supports unbounded-context execution, and keeps online inference latency low. Across multiple challenging 3D open-world games, Gamer demonstrates solid generalization and operational efficiency comparable to skilled players. It also achieves competitive results on a range of conventional 2D game benchmarks. These results suggest that even repetitive keyboard and mouse trajectories can support substantial gains from scaling data and learning algorithms. Training on these trajectories helps Gamer learn complex skills more steadily in environments with both physical and digital properties. This approach offers a path toward generalist agents that can interact across digital and physical worlds.