Research talk: Reinforcement learning with preference feedback
About this video
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceResearch talk on reinforcement learning with preference feedback. Teaches techniques for learning from human preferences rather than explicit rewards.
A 14-minute video from Microsoft Research: “Research talk: Reinforcement learning with preference feedback”.
Video by Microsoft Research, played through YouTube's embedded player.
Part of Science | Reinforcement Learning | Microsoft Research Summit 2021