jonbaer
7 hr. ago

CS234: Reinforcement Learning Winter 2025

78
8
S
sillysaurusx
4 hr. ago
It’s been said that RL is the worst way to train a model, except for all the others. Many prominent scientists seem to doubt that this is how we’ll be training cutting edge models in a decade. I agree, and I encourage you to try to think of alternative paradigms as you go through this course.

If that seems unlikely, remember that image generation didn’t take off till diffusion models, and GPTs didn’t take off till RLHF. If you’ve been around long enough it’ll seem obvious that this isn’t the final step. The challenge for you is, find the one that’s better.

P
paswut
2 hr. ago
What about for combinatorial optimization? When you have a simulation of the world what other paradigms are fitting
W
whatshisface
4 hr. ago
RL is barely even a training method, its more of a dataset generation method.
K
kgarten
4 hr. ago
Are the videos available somewhere?

spring course is on YouTube https://m.youtube.com/playlist?list=PLoROMvodv4rN4wG6Nk6sNpT...

Z
zerosizedweasle
5 hr. ago
Given Ilya's podcast this is an interesting title.