Improve itself through experimentation with reinforcement learning. This is how ... | Hacker News

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

		tintor on Dec 15, 2022 \| parent \| context \| favorite \| on: Who knew the first AI battles would be fought by a... Improve itself through experimentation with reinforcement learning. This is how humans improve too. AlphaZero does it.

lostmsu on Dec 15, 2022 [–]

The amount of work in that area of research is substantial. You will see world shattering results in a few years.

Current SOTA: https://openai.com/blog/vpt/

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