Training AI Without Writing A Reward Function, with Reward Modelling
Robert Miles AI Safety · 3 则 HN 推荐
视频问答
可以让 AI 解释当前片段，或总结整部视频。如果回答附有时间戳，点击即可跳到对应片段。
试着问：这里讲的是什么意思？
需要用 Google 登录。确认前可查看最多会扣除多少积分。
Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.
HN 推荐的原因： Seen as the clearest introduction to the idea behind RLHF, and also borrowed by commenters as a metaphor for human motivation.
“I find this video by Rob Miles still the best presentation of the ingenious original 2017(!) paper” 阅读 HN 讨论 ↗