We use sim2real with distillation-based transfer :)
This means no need to do the rollouts on real robots first! Please check out https://sgs-rl.github.io for some transfer examples (albeit a simpler setting then the multi-part NIST board we examine in AlphaNIST).
The mechanism is loosely related to curriculum learning, though we argue there are some distinctions. In the methodological companion paper (https://sgs-rl.github.io), we try to get into more details in the related work and baselines including comparison to methods like PLR (also from Deepmind), SFL, and linear handcrafted curriculums over states.
You are giving me some inspiration, though, that it might be good to try to explain the related techniques in a lower-dimensional setting to help teach the concept more effectively! brb
If you're interested in some more details, take a look at this post I made (and am admittedly still polishing) that discusses the method in a low-dimensional space. I am trying to make it more accessible to the community since explaining it for higher-dimensional robot control / hybrid-contact dynamical systems is a whole other thing :)
We can answer questions! But also, I want to highlight that the "AlphaNIST" name is an homage to the very well known work from David Silver's research group @ Deepmind circa 2016->2018. This was when we were coming up very early in our research careers and their work obviously had a big impact on us!
It has taken longer to make some of those ideas work for areas as challenging as robotics where there are physical constraints to deal with (and admittedly in this paper, we do not show the transfer to real hardware quite yet). But, we have some glimmer of evidence it is looking possible here (in another recent paper) that we cranked on for the last 6 months and will be featured at CoRL: https://x.com/octi_zhang/status/2108583315544682914
We are also all mega-lurkers here so we were honored to be featured on the front page!
As far as I know Apple also does not own "i" or McDonalds owns "Mc".
If you're creating a Burger called McSomething or a device called iWhatever it does not feel like "paying homage" to Apple/McDonalds, it feels more like copying and trying to capture some audience from this bigger player.
That's because Google Deepmind has consistently used AlphaSomething for their scientific models. Not for their consumer models which are Gemini, but their models which are more cutting edge and specific to niche problems.
Ah, I see, Ireland and McKinsey are trying to copy and capture McDonalds audience. /s
Yes, you said burger, but also AlphaNIST is not a technology conglomerate holding company. And the term Alpha is not at all used in their products. It's neither Alpha Phones, not AlphaGemini, nor is Google called Alpha. More than that Alphabet is never shortened Alpha.
I would strongly argue against that. I would argue that Google Deepmind has consistently used AlphaSomething for their scientific models. Not for their consumer models which are Gemini, but their models which are more cutting edge and specific to niche problems.
Got any in a single category which all start with Alpha and named by the same organization? Say something like... I don't know... Deep learning models published by Google?
If there's 10 breakfast cereals from the same company all starting with Alpha, I would give you some credit. But like this I don't even know what your reply is trying to tell me.
I honestly feel like I am taking crazy pills here.
OK I'm telling you that I'm not as keen as you are to cede every possible name that starts with "Alpha" to Google.
And to answer your question directly, DEC had a whole series of things called "Alpha". eg AlphaStation family of workstations, the Alpha AXP series of processors etc (alpha 21064, alpha 21164, alpha 21264, alpha 21364).
Point received! We wonder what a better way to pay that same homage would be, since we followed the similar philosophy, but with considerations for our contact-rich robotic control setting.
Very cool line of work and emergent behaviors are so fascinating and solving NIST standard is very impressive! This just shows robot dexterity doesnt necessarily always need hands atleast for industrial assembly tasks.
Came across your CoRL publication before I found alphaNIST. I was curious how much simulation asset engineering and sysID/tuning was needed for transfer to the real robot?
Ensuring the assets are "CAD-level accurate" has a huge impact on making this work in practice. So much so, that our collaborators Yash Narang [1] and Iretiayo Akinola [2] have spent a number of years on just this - we are standing on the shoulders of giants!
Additionally, understanding the hardware well (including things like motor and controller dynamics) is non-negotiable. We learned the hard way that there is, in fact, no free lunch. You really have to get the deep understanding of physics and engineering right.
We are seeing increasing evidence that these sort of video world models are terrible options for useful rollouts of the physical dynamics of the environment. It is hypothesized that you can get them to be better than simulators by training on physics simulation data, but then the question becomes, why not use the simulator directly?
There are a lot of areas where predictive models make sense in the robotics stack, but doing it with "video world models" as is trendy this year is likely a bet in the wrong direction according to the evidence we have been amassing in the last 6 months.
I had a lot of fun playing this! It's definitely the quirkiness that sets it apart from the typical "GenAI" content. Highly recommend other hackernews readers check it out.
thats just not in the BDs ethos. They have been the only company really trying to physically build these kinds of robust, dynamic systems for the last 3 decades (almost to a fault).
Thank you for thinking of this and implementing it!
But, I'm wondering is there any major difference between just clicking the "..." next to the song in the default interface and selecting "Download->Audio"?
You need to create an account to access download links (and I only see this option for songs I've generated). However, it looks like each link simply points to an mp3 file based on the song id. eg:
1. Open the website https://app.suno.ai/.
2. Click on the share button above any song to obtain the share URL.
3. Paste the URL onto our website https://sunoaidownload.com/.
4. Click 'Download'.
