Ouyang et al. (2022), stating that they build on reinforcement learning from human feedback, cite Christiano et al. (2017), with Ibarz et al. (2018), for its original development on simulated robots and Atari games.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Training language models to follow instructions with human feedback → attributes to → Deep reinforcement learning from human preferences
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.