
Jacob Beck and Risto Vuorio
TalkRL: The Reinforcement Learning Podcast
00:00
Do We Really Need Rl?
Rl has been a meme that's been popping up every once in a while more recently is that do we even need rl like yon lakun had you know a slide not long ago saying basically let's try to either minimize rl or or use um more like uh shooting methods and learn better models. i think if i'm not misremembering i think michael litman former advisor would you know definitely fall into that camp so i think we could make a lot of people less upset by not saying that that's not rl for plus maybe comment number one comment number two is we really shouldn't do rl at all.
Transcript
Play full episode