Fine-tuning RL Models is Secretly a Forgetting Mitigation Problem - Mate Time!
Machine Learning and AI Academy
0:00 / 0:00
Fine-tuning RL Models is Secretly a Forgetting Mitigation Problem - Mate Time!
411 просмотров · 2 г. назад
Machine Learning and AI Academy
10,9 тыс. подписчиков
411 просмотров · 2 г. назад
#rl #machinelearning #ai
00:00 Introduction
02:11 The Problem
13:36 The Forgetting Experiment
15:30 Net Hack Problem
27:04 New SOTA on Net Hack
35:02 Summary and Discussion
