Skip to content

Is there any difference between this and the knowledge distillation of GPT-4o ? #26

@ningkp

Description

@ningkp

reasoning by GPT-4o + Rule-based Reward + GRPO = reasoning by GPT-4o + SFT

This is not a real RL; it is supervised learning. Just like the image classification, and the reward is the $1{\hat{y}==y^*}$. It also can employ RL optimization (like PPO or GRPO) to learn the supervised model, but it is not a real RL.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions