Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 11 months ago

MODERATORS

communick@academy.garden

[D] What's this new Q* algorithm in relation to OpenAI breakthrough ? (alien.top)

submitted 10 months ago by to4life4@alien.top to c/machinelearning@academy.garden

3 comments fedilink hide all child comments

I heard about this on Twitter from some people in the field, in relation to OpenAI's new breakthrough.

Is there a summary paper, like the 'All you need is attention' paper, that goes over this?

Also, how specifically does this relate to and/or add on to Large Language Models?

Cheers

top 3 comments

sorted by: hot top controversial new old

[–] AdEarly832@alien.top 1 points 10 months ago

So, what about https://arxiv.org/pdf/2310.04406v1.pdf ? LANGUAGE AGENT TREE SEARCH UNIFIES REASONING ACTING AND PLANNING IN LANGUAGE MODELS. For me, it looks like very similar. The results are 98% on HumanEval

[–] FernandoMM1220@alien.top 1 points 10 months ago

I assume its similar to Q learning.

The star implies its a pathfinding algorithm which Q learning already kinda is.

[–] Western-Image7125@alien.top 1 points 10 months ago

“All you need is attention” made me twitch my eyes a little