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

Agents that imagine and plan

deepmind.com

Post reply on HN
Print view View original

11–20 of 62 posts

Re: Agents that imagine and plan

#11

Post by PeterisP »

GuiA wrote: post #9
habitue wrote: post #8

Earlier quoted context omitted.

The human brain has specialized structures in it, it isn't a homogeneous mass from which all parts of human cognition emerge once you have enough brain cells (see elephant brain size vs. human brain size). If you've ever seen anything else designed by evolution, you'll know it generally tends to be a grab-bag of weird tricks all combined together in a way that somehow works. We don't know what all the tricks are, nor…

> If you've ever seen anything else designed by evolution, you'll know it generally tends to be a grab-bag of weird tricks all combined together in a way that somehow works. We don't know what all the tricks are, nor which are necessary or sufficient to create human-like intelligence. That is precisely the core of my interrogation. The papers mentioned in the article seem to be about "hand designing" the weird tricks…

> shouldn't the goal be to build a system that enables the emergence of these weird tricks without involving human design

It depends on your goals - if your goal is to build a system that can perform smart actions (e.g. build/simulate something comparable to a brain), then that's not required (it may happen to be useful, or not); if your goal is to build a system that can create and build systems that can perform smart actions (e.g. build/simulate something comparable to the evolution process of an intelligent species) then it should.

Re: Agents that imagine and plan

#12

Post by virtuabhi »

eduren wrote: post #7
GuiA wrote: post #3

Why do we need to explicitly design architectures such as the "imagination encoder" the article describes? A proposed long term goal of deep learning is to have AI that surpasses human cognition (e.g. DeepMind's About page touts that they are "developing programs that can learn to solve any complex problem without needing to be taught how"), which was not explicitly designed in terms of architectural components such…

>Shouldn't imagination and planning be observed spontaneously as emergent properties of a sufficiently complex neural network? Not necessarily. I think it comes down to what you mean by "sufficiently complex". If we took a classic feedforward Multi-Layer Perceptron and gave it massive amounts of good data, a long time to train, and a nearly unbounded network size, I'm not sure it would ever develop architecture withi…

> Although it would be fun to try producing human level intelligence by seeding a physics simulation of primordial soup and letting it run for millions of "years", I don't think that's feasible for most researchers.

And what would be the seed for random number generator?

Re: Agents that imagine and plan

#13

Post by aqsalose »

The obvious caveat: this is quite far away from my field of expertise. Doubly so, because I'm not an expert in neural net ML and neither in cognitive science. So take this with spoonful of salt. But anyhow, I don't like the word "imagine" here. It seems suggest cognitive capabilities that their model probably does not have.

As far as I do understand the papers, their model builds (in unsupervised fashion which sounds very cool) an internal simulation of the agent's environment and runs it to evaluate different actions, so I can see why they'd call it imagination / planning, because that's the obvious inspiration for the model and so it sort of fits. But in common parlance, "imagination" [1] also means something that relatively conscious agents do, often with originality, and it does not seem that their models are yet that advanced.

I'm tempted to compare the choice of terminology to DeepDream, which is not exactly a replication of the mental states associated with human sleep, either.

[1] https://en.wikipedia.org/wiki/Imagination

Re: Agents that imagine and plan

#14

Post by habitue »

PeterisP wrote: post #10
ansgri wrote: post #2

https://en.wikipedia.org/wiki/Model_predictive_control Of course imagining possible outcomes before executing is useful! And it has many uses outside deep learning. No reason to reinvent new words, really. At least without referring to the established ones. Maybe there is a serious novel idea, but I've missed it. Basically, if you need to control a complex process (i.e. bring some future outcome in accordance to your…

The link between imagining and deep learning is rather in the opposite direction - it has always been obvious that imagining possible outcomes before executing would be useful, but the novelty is that deep learning has allowed them to actually make "imagination" that works. MPC is an useful concept if you have a predictive model that's at least vaguely close to the actual behavior. In some contexts (e.g. modeling of…

> systems that can construct such a predictive model/imagination from experience

I just want to emphasize this point as the crux here. We have many many techniques for AI that involve doing roll-outs once a smart human with domain knowledge hands the system a fully-formed model of the dynamics. Not so many where the dynamics are learned

Re: Agents that imagine and plan

#15

Post by eduren »

GuiA wrote: post #9
habitue wrote: post #8

Earlier quoted context omitted.

The human brain has specialized structures in it, it isn't a homogeneous mass from which all parts of human cognition emerge once you have enough brain cells (see elephant brain size vs. human brain size). If you've ever seen anything else designed by evolution, you'll know it generally tends to be a grab-bag of weird tricks all combined together in a way that somehow works. We don't know what all the tricks are, nor…

> If you've ever seen anything else designed by evolution, you'll know it generally tends to be a grab-bag of weird tricks all combined together in a way that somehow works. We don't know what all the tricks are, nor which are necessary or sufficient to create human-like intelligence. That is precisely the core of my interrogation. The papers mentioned in the article seem to be about "hand designing" the weird tricks…

Hand designing is the only feasible option available to us. A system that could architect itself would either need:

A bootstrap intelligence in order to self-plan, self-experiment, and self-modify. Escher hands drawing each other basically... or

Similar conditions to our only known spontaneous intelligence (us). That includes some sort of base code (genetics), competitive environments for rewarding good architectures, and lots of time in simulation. No guarantee this would work either.

Re: Agents that imagine and plan

#16

Post by eduren »

virtuabhi wrote: post #12
eduren wrote: post #7

Earlier quoted context omitted.

>Shouldn't imagination and planning be observed spontaneously as emergent properties of a sufficiently complex neural network? Not necessarily. I think it comes down to what you mean by "sufficiently complex". If we took a classic feedforward Multi-Layer Perceptron and gave it massive amounts of good data, a long time to train, and a nearly unbounded network size, I'm not sure it would ever develop architecture withi…

> Although it would be fun to try producing human level intelligence by seeding a physics simulation of primordial soup and letting it run for millions of "years", I don't think that's feasible for most researchers. And what would be the seed for random number generator?

"Let there be light"

Re: Agents that imagine and plan

#18

Post by habitue »

GuiA wrote: post #9
habitue wrote: post #8

Earlier quoted context omitted.

The human brain has specialized structures in it, it isn't a homogeneous mass from which all parts of human cognition emerge once you have enough brain cells (see elephant brain size vs. human brain size). If you've ever seen anything else designed by evolution, you'll know it generally tends to be a grab-bag of weird tricks all combined together in a way that somehow works. We don't know what all the tricks are, nor…

> If you've ever seen anything else designed by evolution, you'll know it generally tends to be a grab-bag of weird tricks all combined together in a way that somehow works. We don't know what all the tricks are, nor which are necessary or sufficient to create human-like intelligence. That is precisely the core of my interrogation. The papers mentioned in the article seem to be about "hand designing" the weird tricks…

> shouldn't the goal be to build a system that enables the emergence of these weird tricks without involving human design?

Two comments:

1. Just because evolution came up with them for humans, doesn't mean if we run an evolutionary algorithm we'll come up with an intelligent system in any reasonable amount of time. There's no reason to believe it's easy to evolve such systems given that we only know of one human-level intelligence in the universe, and it seems to have taken billions of years to come about.

2. This is unnecessarily tying our hands. Evolution often builds very inefficient, overly complicated versions of things that can be simplified dramatically once humans understand the underlying principles behind why they work. In addition we have a huge body of theoretical work on planning, decision theory etc that improves dramatically on our natural learning processes that we can take advantage of. We get no points for not "cheating" here.

Re: Agents that imagine and plan

#19

Post by PeterisP »

aqsalose wrote: post #13

The obvious caveat: this is quite far away from my field of expertise. Doubly so, because I'm not an expert in neural net ML and neither in cognitive science. So take this with spoonful of salt. But anyhow , I don't like the word "imagine" here. It seems suggest cognitive capabilities that their model probably does not have. As far as I do understand the papers, their model builds (in unsupervised fashion which sound…

Can you elaborate on what qualitative difference do you see between imagination-as-you-understand-it and an internal simulation of a nonexistent (maybe future, maybe never happening) state of an agent's environment or inputs? There's an obvious quantitative difference - their environment is much simpler than ours, and their "imagination" is bound to imagining the near future (unlike us), but conceptually, where do you see the biggest difference?

Originality seems not to be the boundary, since even this simple model seems to imagine world states that they never saw, never will see, and possibly even aren't possible in their environment, i.e. they are "original" in some sense.

If I look at the common understanding of "imagination" and myself, what can I imagine? I can imagine 'what-if' scenarios of my future, e.g. what could be the outcome if I do this or that, or if something particular happens; I can imagine scenarios of my past, i.e., "replay" memories; I can imagine counterfactual scenarios that never happened and never will; I can imagine various senses - i.e. how a particular melody (which I'm "constructing" right now, iteratively, with the help of this imagination to guide my iterations) might sound when played in a band, or how something I'm drawing might look like when it's completed - all of this seems different variations on essentially the same thing, which is an internal simulation (model) generating data about various hypothetical states.

This might be used to evaluate different actions, but it might also be used to simply experience these states (i.e. daydream) or do something else - that's more of a question on how the agent would want to use the "imagination module", not a particular property of the imagination/internal simulation model itself.

Re: Agents that imagine and plan

#20

Post by Cybiote »

aqsalose wrote: post #13

The obvious caveat: this is quite far away from my field of expertise. Doubly so, because I'm not an expert in neural net ML and neither in cognitive science. So take this with spoonful of salt. But anyhow , I don't like the word "imagine" here. It seems suggest cognitive capabilities that their model probably does not have. As far as I do understand the papers, their model builds (in unsupervised fashion which sound…

I agree with you. I remember skimming the paper and finding it interesting but wondered if selecting that term might set too many imaginations running. I don't have a problem with their calling it imagination, though.

But consider that many would object if I stated jumping spiders have an active imagination. Yet, this is not far fetched if you accept that imagination includes planning against a learned model.

Insects are known to be capable of learning. They need to be able to remember routes or learn which locations to prefer or avoid. Jumping spiders are known for their ability to carry out and hold complex plans in their head. Though a form of imagination, most would hesitate to call it that.

(1) http://science.sciencemag.org/content/355/6327/833, https://youtu.be/exsrX6qsKkA?t=44s

Post reply on HN