英文名称:Deep Reinforcement Learning from Human Preferences
中文名称:从人类偏好中进行深度强化学习
链接:https://arxiv.org/abs/1706.03741
作者:Paul F Christiano, Jan Leike, Tom B Brown...
机构:OpenAI, …
“Data” in machine learning can be almost anything you can imagine. A table of big Excel spreadsheet, images, videos, audio files, text and more.
机器学习其实可以分为两部分
将不管是什么data,都转成numbers.挑选或者建立一个模型来学习这些numbers …