Jeff Clune
TalkRL: The Reinforcement Learning Podcast
The Non-Causal Model of Predicting the Next State in a Stack of Frames
This is a special case of Jan LeCun's cake where the bulk of the work was this unsupervised or self supervised training, but you had this extra step here. You were able to use all this unlabeled data and I guess turn it into labeled data. The overall project took about a year and a half to get it all to actually work. But yeah, it wasn't like we set off with the goal to do something vaguely in this space and eventually through trial and there we got to here.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
