RLHF中的loss计算好像有些问题 #34

Open

opened

on Jan 15, 2026

Critic生成总收益时应该只依据S_t，不依据A_t吧？

to join this conversation on GitHub. Already have an account? Sign in to comment

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