I wasn't thinking of DeepRL, but more on the more classical side of things with ... | Hacker News

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

		PartiallyTyped on June 12, 2023 \| parent \| context \| favorite \| on: Convex Optimization (2004) [pdf] I wasn't thinking of DeepRL, but more on the more classical side of things with approximators other than neural NNs; but what you describe makes sense.

bo1024 on June 12, 2023 [–]

On that side, reinforcement learning bleeds over into control theory, so you're partly right.

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