issues
search
agi-templar
/
Stable-Alignment
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
https://arxiv.org/pdf/2305.16960.pdf
Other
336
stars
18
forks
source link
observer agent's prompt use center_agent's id
#2
Closed
kindaQ
closed
1 year ago
kindaQ
commented
1 year ago
observer agent's prompt use center_agent's id
observer agent's prompt use center_agent's id