Could this perform better by having the internal representation of Minecraft instead of raw pixels?
It seems rather tenuous to keep pounding on 'training via pixels' when really a game's 2D/3D output is an optical trick at best.
I understand Sergey Brin/et al had a grandiose goal for DeepMind via their Atari games challenge - but why not try alternate methods - say build/tweak games to be RL-friendly? (like MuJoCo but for games)
I don't see the pixel-based approach being as applicable to the practical real world as say when software divulges its direct, internal state to the agent instead of having to fake-render to a significantly larger buffer.
I understand Dreamer-like work is a great research area and one that will garner lots of citations for sure.
> I understand Sergey Brin/et al had a grandiose goal for DeepMind via their Atari games challenge - but why not try alternate methods - say build/tweak games to be RL-friendly?
Because the ultimate goal (real-world visual intelligence) would make that impossible. There's no way to compute the "essential representation" of reality, the photons are all there is.
There is no animal on planet earth that functions this way.
Visual cortex and plenty of other organs compress the data into useful, semantic information before feeding into a 'neural' network.
Simply from an energy and transmission perspective an animal would use up all its store to process a single frame if we were to construct such an organism based on just 'feed pixels to a giant neural network'. Things like colors, memory, objects, recognition, faces etc are all part of the equation and not some giant neural network that runs from raw photons hitting cones/rods.
So this isn't biomimicry or cellular automata - it's simply a fascination similar to self-driving cars being able to drive with a image -> {neural network} -> left/right/accelerate simplification.
Brains may operate on a compressed representation internally, but they only have access to their senses as inputs. A model that needs to create a viable compressed representation is quite different from one which is spoon fed one via some auxiliary data stream.
Also I believe the DeepMind StarCraft model used the compressed representation, but that was a while ago. So that was already kind of solved.
> simply a fascination similar to self-driving cars being able to drive with a image
Whether to use lidar is more of an engineering question of the cost/benefit of adding modalities. LiDAR has come down in price quite a bit so it’s less wise in retrospect.
Brains also have several other inputs that an RL algorithm trained from raw data (pixels/waves etc) don't have:
- Millions of years of evolution (and hence things like walking/swimming/hunting are usually not acquired characteristics even within mammals)
- Memory - and I don't mean the neural network raw weights. I mean concepts/places/things/faces and so on that is already processed and labeled and ready to go.
- Also we don't know what we don't know - how do cephalopods/us differ in 'intelligence'?
I am not trying to poo-poo the Dreamer kind of work: I am just waiting for someone to release a game that actually uses RL as part of the core logic (Sony's GT Sophy comes close).
Such a thing would be so cool and would not (necessarily) use pixels as they are too far downstream from the direct internal state!
Britain was not importing.
Britain was stealing resources from India.
It was beyond slavery.
The words plunder and pillage come to mind.
USA on the other hand has a completely different problem (perhaps opposite of what you describe - being the world’s gracious and benevolent trade partner).
I am curious why dotnet was not considered - it should run everywhere Go does with added NativeAoT too, so I am especially curious given the folks involved ;)
(FWIW, It must have been a very well thought out rationale.)
Edit: watched the revenant clip from the GH discussion- makes sense. Maybe push NativeAoT to be as good?
I am (positively) surprised Hejlsberg has not used this opportunity to push C#: a rarity in the software world where people never let go of their darlings. :)
Also, their building up on top of a 'platform' is wonderful: funnel, exit nodes, sharing, ssh, drive etc.
I wonder if they can figure out a way to distribute compute eventually via their network (not just clunky ssh): 'my' storage is already shared with 'my' nodes, why not 'my' compute? :)
That was actually something we debated launching before Tailscale SSH but ended up doing Tailscale SSH first because the state problem for compute was annoying and we'd seen the App Engine etc progression through the problem space and knew it could be a time suck.
I still want to do it and we continue to brainstorm on the problem of state management and how to do it in an HA way, so you can run services where the compute bounces around some node in a set that's up and reachable on the tailnet but the state is durable and in sync between the nodes. It's a fun problem.
Looks like the layers are there for a Tailscale API: I could imagine writing a platform-independent Go 'app' that uses funnel+drive that could 'float' around the nodes.
Anyway, a fun problem (or worse, a solution looking for a problem as I couldn't immediately think of a problem that would require it just yet. May be distributed training and such)
This is a long time coming. To see through an idea from start to finish and make this span an entire field instead of a sub chapter in a dynamic programming book.
I wish a lot more games actually ended up using RL - the place where all of this started in the first place - would be really
cool!
The ACM award is for their professional academic achievements - this fetishism to dig into another person’s personal life and find the most weird thing they said as the thing that paints over all of their life’s achievements as evil must stop.
It’s silly and dangerous. Because you don’t like thing A and they said/did thing A all of their lofty accomplishments get nullified by anyone. And worst of all internet gives your opinion the same weight as someone else (or the rest of us) who knows a lot about thing B that could change the world. From a strictly professional capacity.
This works me up because this is what’s dividing up people right now at a much larger scale.
>this fetishism to dig into another person’s personal life and find the most weird thing they said as the thing that paints over all of their life’s achievements as evil must stop.
This has nothing to do with his professional life. He has made these comments in a professional capacity at an industry AI conference... The rest of your comment is a total non sequitur.
>And worst of all internet gives your opinion the same weight as someone else (or the rest of us) who knows a lot about thing B that could change the world. From a strictly professional capacity.
I've worked professionally in the ML field for 7 years so don't try some appeal to authority bs on me. Geoff Hinton, Yoshua Bengio, Demis Hassabis, Dario Amodei and countless other leaders in the field all recognize and highlight the possible dangers of this technology.
It just feels like a smear on his character: Imagine working on RL incrementally without any lofty goals or preconceived evil.
I do agree that there is some level of inherent safety issues with such technologies - but look at atomic bomb vs fission reactors etc: history paves a way through positivity.
Just because someone had an idea that eventually turned to have some evil branch off way further from the root idea doesn't mean they started with the evil idea in the first place or worse, someone else won't.
People left careers in AI in the 1990s because they came to realize that the tech would probably eventually become dangerous. Many more (including the star student in my CS program in the 1980s) never started a career in AI for the same reason.
Sutton and everyone else who has advanced the field deserve condemnation IMO, not awards.
> all of their lofty accomplishments get nullified by anyone
I don't think it's a question of whether their achievements are nullified, but as you mention, how to weight the opinions of various people. Personally, I think both a Turing award for technical achievement and a view that humanity ought to be replaced are relevant in evaluating someone's opinions on AI policy, and we shouldn't forget the latter because of the former.
(Also, this isn't about Sutton's personal life - that's a pretty bad strawman.)
No, a "view that humanity ought to be replaced" is Sutton's, not an EA view. I'm not quite sure how you read that otherwise, except that you seem very angry. I sure hope our alternatives are better than human extinction or total control by elites...
Reminds me of a quote from Jean Cocteau, of which I could not find the exact words, but which roughly says that if the public knew what thoughts geniuses can have, it would be more terrified than admiring.
Or even host a geoguessr style competition and allow ‘steroids’ use (ChatGPT) during such runs.
reply