News for hackers. Stuff that matters.
Re:Visual Q-Learning Demo in JavaScript from Karpathy (2013) by cubefox on Saturday November 25, 2023 @10:56PM (#38419045)
But the recent breakthrough in AI isn't based on Q learning, but on self-supervised learning. Reinforcement learning is only used for part of the fine-tuning of those SSL models.

There are no comments on this comment yet.