Skip to content

如果只是想学大模型后训练包括dpo ppo grpo这些po算法的话，需要从0读起吗 #8

Open
Open
如果只是想学大模型后训练包括dpo ppo grpo这些po算法的话，需要从0读起吗#8
@northhorse0208

Description

@northhorse0208
northhorse0208
opened on May 2, 2026

感觉现在大模型领域的rl算法和这些之前的rl算法相差甚远啊

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions