Dynamic programming and reinforcement learning are just diagonalizations of the ... | Hacker News

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

		adamnemecek on April 5, 2021 \| parent \| context \| favorite \| on: Predictive coding has been unified with backpropag... Dynamic programming and reinforcement learning are just diagonalizations of the Young tableau. This is related to the spectral theorem.

selimthegrim on April 6, 2021 [–]

Interesting. Is there some concrete realization you had in mind?

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