What's _online_ RL for an LLM? Saw this on the llama 3.3 reports too... | Hacker News

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

		eggie5 8 months ago \| parent \| context \| favorite \| on: OpenAI Reinforcement Fine-Tuning Research Program What's _online_ RL for an LLM? Saw this on the llama 3.3 reports too...

whimsicalism 8 months ago [–]

Online RL for LLMs means you are sampling from the model, scoring immediately, and passing gradients back to the model.

As opposed to, sampling from the model a bunch, getting scores offline, and then fine tuning the model on those offline scored generations.

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