OpenAI News·· 2022-06-23AI 评分47
OpenAI 通过 Video PreTraining 训练神经网络玩 Minecraft
Learning to play Minecraft with Video PreTraining
AI 导读
OpenAI 利用海量无标签人类游戏视频进行 Video PreTraining，仅结合少量标注数据即训练出能玩 Minecraft 的神经网络。该模型经微调后可完成制作钻石工具任务，通常需熟练人类耗时超 20 分钟（约 24,000 次操作）。其直接模拟人类键鼠输入接口，具备通用性，是迈向通用计算机使用智能体的一步。
原文
We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our model uses the native human interface of keypresses and mouse movements, making it quite general, and represents a step towards general computer-using agents.
来源：OpenAI News · openai.com