RLHF and its missing component
Machine Learning and AI Academy
0:00 / 0:00
RLHF and its missing component
3 129 просмотров · 2 г. назад
Machine Learning and AI Academy
10,9 тыс. подписчиков
3 129 просмотров · 2 г. назад
#ai #agi #machinelearning
00:00 MPDs and Reward Shaping
18:40 RLHF & Its problems
34:29 Identifying the Problem
41:12 PARL the Solution
52:06 Discussion and the Review Process
