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

DeepMind says reinforcement learning is ‘enough’ to reach general AI

venturebeat.com

Post reply on HN
Print view View original

31–40 of 312 posts

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#31

Post by virgilp »

randcraw wrote: post #8
ramraj07 wrote: post #5

Wait 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.

Wait no, that can't be true. Finite state machines are only as powerful as regular expressions; you need pushdown automata even for programming languages, surely you can't model natural language with finite state machines? (maybe an infinite number of them, but I'm doubtful even on that - I'd have to review the theory to be sure though)

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#32

Post by visarga »

dannyw wrote: post #22

Alternate title: DeepMind fails to make progress on AGI, publishes thought piece instead.

And the entitlement we have is even higher than the difficulty of the task and the hard work people are putting in. Anyone here can say they did as much for RL?

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#34

Post by webmaven »

visarga wrote: post #26
webmaven wrote: post #3

Saying 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.

RL + piggybacking on human culture might be enough, or evolution + RL for biological agents.

> RL + piggybacking on human culture might be enough, or evolution + RL for biological agents.

Yes, but over what timeframe? Will there be any diminishing returns plateaus along the way?

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#35

Post by visarga »

jjjdjjddddsfsd wrote: post #25

Are the just reformulating the principles of evolution in digital terms, and essentially not providing any new insights at all? Yes, intelligence has been created by evolution. That doesn't imply that any system that is subject to evolutionary forces will lead to the creation of intelligence (and not within a reasonable timeframe, either). The challenge is to create a system that is capable of evolving intelligence.…

Evolutionary algorithms are tricky, just like deep learning. It's not "just reformulating the principles of evolution in digital terms, and essentially not providing any new insights".

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#37

Post by visarga »

qwertywert_ wrote: post #12
adipandas wrote: post #2

This 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].

Yea. For animals, reproduction and just surviving is the reward function? It talks a lot about having a rich enough environment for learning which makes sense, if a computer lives only in a Go board it can only learn go playing itself. How do you simulate a rich enough environment purely in software (or do you sense input from the "real" environment) and what reward do we define in this complex environment.. It seems…

You put many agents in the same environment, agents are both actors and the environment.

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#38

Post by frostburg »

virgilp wrote: post #31
randcraw wrote: post #8

Earlier quoted context omitted.

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.

Wait no, that can't be true. Finite state machines are only as powerful as regular expressions; you need pushdown automata even for programming languages, surely you can't model natural language with finite state machines? (maybe an infinite number of them, but I'm doubtful even on that - I'd have to review the theory to be sure though)

It is true; keep in mind that real computers are strictly speaking FSMs, not Turing machines, due to having a finite "tape". It's just vastly more useful to think of them as such when programming.

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#39

Post by skybrian »

virgilp wrote: post #31
randcraw wrote: post #8

Earlier quoted context omitted.

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.

Wait no, that can't be true. Finite state machines are only as powerful as regular expressions; you need pushdown automata even for programming languages, surely you can't model natural language with finite state machines? (maybe an infinite number of them, but I'm doubtful even on that - I'd have to review the theory to be sure though)

In practice, both people and machines can only handle a finite amount of nesting, so you could do it though it would be awkward to express.

Re: DeepMind says reinforcement learning is ‘enough’ to reach general AI

#40

Post by webmaven »

jjjdjjddddsfsd wrote: post #25

Are the just reformulating the principles of evolution in digital terms, and essentially not providing any new insights at all? Yes, intelligence has been created by evolution. That doesn't imply that any system that is subject to evolutionary forces will lead to the creation of intelligence (and not within a reasonable timeframe, either). The challenge is to create a system that is capable of evolving intelligence.…

> Afaik some biologists even think that the evolution of intelligence was rather unlikely and would not necessarily happen again under the same circumstances as on earth.

Hmm. Can you provide a pointer to those biologists?

AFAIK, high intelligence has arisen more than once on Earth (Hominoids, Cetaceans, Octopuses), so I'm somewhat skeptical of that claim, but perhaps they're construing intelligence more narrowly (ie. only Homo Sapiens qualifies).

Post reply on HN