Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Q-Transformer

qtransformer.github.io

Post reply on HN
Print view View original

31–40 of 74 posts

Re: Q-Transformer

#31

Post by Workaccount2 »

brcmthrowaway wrote: post #10

It's clear we're searching for the god algorithm of AI, just like physicists are searching for theory of everything. Are transformers the answer though?

It seems more likely that there will be multiple avenues to AGI, all with their strengths and weaknesses. But perhaps the "God AI" will be a multifaceted model composed of many different models acting in unison.

Re: Q-Transformer

#32

Post by px43 »

Philpax wrote: post #5

Worth noting that this came from DeepMind in Sep-Oct of this year, so it's not related to OpenAI's "unfortunate" leak [0] of Q*. [0] https://www.theverge.com/2023/11/29/23982046/sam-altman-inte...

I wouldn't go that far. Immediately after Q* leaked, Jimmy Apples pointed to this thread on Twitter : https://twitter.com/polynoamial/status/1676971508911198209

It's Noam Brown's (former Deep Mind) "I'm joining OpenAI" thread from Back in June, and he talks about how he wants to bring some of the work from AlphaGoZero etc into OpenAI's AGI architecture.

It looks like this Q-transformer work shares a lot of the same lineage of what Q* is supposed to be. This is Google's attempt at mushing Q-learning into transformer land, which is probably what Q* is as well. It's not the same thing, for sure, but they are at least sibling bodies of work.

Re: Q-Transformer

#33

Post by GaggiX »

maurits wrote: post #8

Being implemented as we speak, by the always impressive LucidRains [1] [1]: https://github.com/lucidrains/q-transformer

It's kinda funny how Lucidrains came back to make numerous commits to this repo following Q*.

Re: Q-Transformer

#34

Post by theptip »

brcmthrowaway wrote: post #10

It's clear we're searching for the god algorithm of AI, just like physicists are searching for theory of everything. Are transformers the answer though?

No, not at all. Just looking for the next step of many, stacking S-curves atop each other.

Re: Q-Transformer

#35

Post by itissid »

Could one of the roomba companies now make those things recognize the objects and avoid them, instead of dead reckoning or RF based obstacle avoidance?

Re: Q-Transformer

#36

Post by itissid »

Just to be clear the "scalable" part here is assuming the dataset of human demonstrations is available it can in a closed loop learn better than before? In other words, am I right in understanding that the mapping from Abstract actions to concrete steps in the State space is provided at a low "enough" cost?

Re: Q-Transformer

#38

Post by itissid »

itissid wrote: post #36

Just to be clear the "scalable" part here is assuming the dataset of human demonstrations is available it can in a closed loop learn better than before? In other words, am I right in understanding that the mapping from Abstract actions to concrete steps in the State space is provided at a low "enough" cost?

Like in Workflow Guided explorations like: https://arxiv.org/pdf/1802.08802.pdf, for example, if you said "Forward the email" the Bot needs to sample from a set of actions which in this case would be DOM elements and the JS API to call to click the right button to forward the email. This would be a harder/interesting to test out. Can it learn to forward an email on firefox desktop browser and then do it on an iphone?

It feels like opening a drawer once learn't, the bot has a (world?) model of what all drawers might look like, so it can open different drawers in any world. But this might not generalize to web interfaces and more specifically, how to do those actions on those interfaces?

Not to take away from what this paper's scope and achievements.

Re: Q-Transformer

#39

Post by falcor84 »

Workaccount2 wrote: post #31
brcmthrowaway wrote: post #10

It's clear we're searching for the god algorithm of AI, just like physicists are searching for theory of everything. Are transformers the answer though?

It seems more likely that there will be multiple avenues to AGI, all with their strengths and weaknesses. But perhaps the "God AI" will be a multifaceted model composed of many different models acting in unison.

Exactly, just as the true god has seven aspects [0].

[0] https://en.wikipedia.org/wiki/Themes_in_A_Song_of_Ice_and_Fi...

Re: Q-Transformer

#40

Post by mikewarot »

brcmthrowaway wrote: post #10

It's clear we're searching for the god algorithm of AI, just like physicists are searching for theory of everything. Are transformers the answer though?

We're searching for an efficient algorithm that leads to AGI. Given sufficient time and compute, I'm sure that we could get there with existing stuff, by accident, and we wouldn't realize it before moving on to the next thing... and there'd be a poor orphan AGI, lost in a Git repo, waiting for runtime.
Post reply on HN