Understanding RL for model training, and future directions with GRAPE | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Understanding RL for model training, and future directions with GRAPE (arxiv.org)
		33 points by sonabinu 7 months ago \| hide \| past \| favorite \| 1 comment

goerz 7 months ago [–]

Don’t people google their newly coined acronyms? GRAPE is already Gradient-Ascent-Pulse-Engineering, which is arguably “machine learning” (optimal control)

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact