GRPO or PPO or some RL

[sourabhY]

Is there a GRPO/RL/PPO for text classification task using encoder only models like bert/roberta.
any github repo , example or help would be really appreciated thanks in advance.

[John6666]

Can we use PPOtrainer to deal with text classification problem

This may be an unresolved issue. The following article may be helpful for general information about GRPO, but it is not specific to classification tasks…

Chapter 1 questions

Hi @Pizofreude, I just published two blog posts about recent RL algorithms for reasoning tasks such as GRPO and Dr. GRPO. You can find them on Medium: The Evolution of Policy Optimization: Understanding GRPO, DAPO, and Dr. GRPO’s Theoretical Foundations Bridging Theory and Practice: Understanding GRPO Implementation Details in Hugging Face’s TRL Library I hope you find it helpful in some way. Thank you, Jen