HackerTube / Video
Training AI Without Writing A Reward Function, with Reward Modelling
Robert Miles AI Safety
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.
Seen as the clearest introduction to the idea behind RLHF, and also borrowed by commenters as a metaphor for human motivation.
6 Hacker News mentions · 2019–2023