rl icon indicating copy to clipboard operation
rl copied to clipboard
verified publisher icon pytorch

[Feature Request] multi-turn reward for RLHF

Open vmoens opened this issue 1 year ago • 2 comments

Implement rewards as proposed in https://arxiv.org/pdf/2405.14655

vmoens avatar Jul 06 '24 07:07 vmoens

I am very interested in multi-turn RLHF, can you give a sample code

ggbondcxl avatar Jul 11 '24 07:07 ggbondcxl

@vmoens I am interested in this. there any progress. I am ready to collaborate or start from scratch.

rghosh08 avatar Oct 05 '24 08:10 rghosh08