this post was submitted on 23 Nov 2023
1 points (100.0% liked)
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 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
OK, so full speculation: this project could be an impl. of Q-Learning (i.e unsupervised reinforcement learning) on an internal GPT model. This would no doubt be an agent model.
Other evidence? The * implies a graph traversal algorithm, which obviously plays a huge role in RL exploration, but also GPT models are already doing their own graph traversal via beam search to do next token prediction.
Are they perhaps hooking up an RL trained model to replace their beam search?
The star in Q* traditionally refers to a policy which is optimal.
Value function, pi is policy
That’s my feeling on what’s actually being reported Poorly by the news
Potential efficacity aside, imagine the scenario of those blabbermouths just eternally yapping among each other and that unbelievably boring wall of text should be what brings about superintelligence :)
I don't think GPT is often used in conjunction with beam search or is it?