DeepMind says reinforcement learning is ‘enough’ to reach general AI
1–10 of 312 posts
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#2This article is interesting, I even skimmed through their paper. But I think still the question remains: How to find the unified reward function? Or in other words, how to find answer to life? [It cannot be 42].
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#3Saying RL is sufficient to (eventually) achieve AGI is a bit misleading. One might similarly state that biological evolution is sufficient to (eventually) achieve biological general intelligence.
Both statements are probably true, but the parenthetical (eventually) is doing an awful lot of heavy lifting.
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#4Saying RL is sufficient to (eventually) achieve AGI is a bit misleading. One might similarly state that biological evolution is sufficient to (eventually) achieve biological general intelligence. Both statements are probably true, but the parenthetical (eventually) is doing an awful lot of heavy lifting.
Yes, it's easy to be convinced on either side, the arguments write themselves. Yes, eventually a learning system might learn enough to be indistinguishable from intelligence. Or this might be entirely the wrong path and detracting from genuine new innovations in how we think about AI.
We won't be able to tell whether it's AGI or just good enough at trained tasks to trick us.
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#5Wait isn’t any Turing complete programming language sufficient to eventually reach general AI
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#6I guess things are slowing down at DeepMind. I have tremendous respect for David Silver and his work on AlphaZero and Richard Sutton as a pioneer in RL. But the cynic in me is that this paper is just a result of Goodhart's law with publishing count as a metric. Any proof of the type of emergent behaviors that they mention from RL with an actual RL experiment would go a long way. Showing an RL agent developing a language would be extremely interesting. It makes me think they tried to show these emergent behaviors but could not and thus ended up with a hypothesis.
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#7This article is interesting, I even skimmed through their paper. But I think still the question remains: How to find the unified reward function? Or in other words, how to find answer to life? [It cannot be 42].
Intelligence would be produced in any Turing complete automata. But the universe has a frame rate of 10^34 (based on Planck constant.) We don't really have the tech to just run "evolution" of a universe or of even a psuedo biological substrate.
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#8Wait isn’t any Turing complete programming language sufficient to eventually reach general AI
Like the notion that all of natural language can be modeled fully if you just use enough finite state machines — surely true; just a wee bit inefficient.
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#9good luck with that. DeepMind should sponsor B. F. Skinner award, to honor the father of their behaviorist theories of 'reward and punishment' as a sort of all-encompassing theory of everything related to cognition. At least now they are torturing GPUs and not some poor lab animals.
on a serious note the only positive outcome of all this shameless PR is that the heavy investment in ML/RL might trickle down to actual science labs and fundamental neuroscience research which might move us forward towards understanding natural intelligence, a prerequisite for creating an artificial one.
Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI
#10Wait isn’t any Turing complete programming language sufficient to eventually reach general AI
Maybe, but that is not helpful in the sense that it doesn't guide research in how to get there.