Well, if I understood correctly, the RL DeepMind implementation is basically mak... | Hacker News

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

BenderV on July 5, 2015 | parent | context | favorite | on: Why Deep Learning Works II: the Renormalization Gr...

Well, if I understood correctly, the RL DeepMind implementation is basically making a RL algorithm work with a supervised model.

sieisteinmodel on July 5, 2015 [–]

This has been done since the 90s. The Deepmind paper is about a few more tricks.

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