Ai Dreams Forum
Artificial Intelligence => General AI Discussion => Topic started by: infurl on March 27, 2018, 10:34:38 pm
-
https://www.youtube.com/watch?v=veWkBsK0nwU
Here is the latest two minute paper presentation, this time about learning to solve complex tasks with sparse rewards by just playing around like a baby. Amazing piece of work.
-
If you think about it, entire evolution is a kind of experiment + punishment / reward system. Each generation has deviations in forms of individuals that correspond to experiments. Unsuccessful individuals fail to mate and die (punishment), while successful pairs pass their genes on the next generations (reward).
I wonder if over an infinite generations cycles, all the successors appear equally each to other. In other words, are there multiple perfection forms, or there is exactly one perfection form. If the later is the case, we could expect advanced aliens from anywhere in this Universe appear exactly like advanced humans.
-
I wonder if over an infinite generations cycles, all the successors appear equally each to other. In other words, are there multiple perfection forms, or there is exactly one perfection form. If the later is the case, we could expect advanced aliens from anywhere in this Universe appear exactly like advanced humans.
I wonder this too. Have you heard of convergent evolution (http://www.zo.utexas.edu/courses/thoc/convergence.html) ? You get animals and other life that evolve into similar forms despite having had no contact, ie; on different continents etc.
This makes me think that Star Trek could have got it right. Again.
-
If there are intelligent aliens they'll either be similar to us, or similar to octopuses. I don't know of any other species that are as intelligent and versatile as those two forms. Evolution isn't about survival of the fittest, it's about survival of the most adaptable, and there many ways to solve that problem. At one extreme you have intelligence and at the other extreme you have vast numbers of bacteria. Both are viable ways for genes to survive. Ironically we still can't survive without all the bacteria that occupy our bodies, but there are many bacteria that are doing just fine without us.
The perfect is the enemy of the good. -- Voltaire
-
I was reading this the other day, but couldn't decide how to bring it up. Now seems perfect, thank you :lightbulb:
https://nypost.com/2018/02/24/heres-what-aliens-probably-look-like/
-
The fittest or adaptable, If the evolution is a punishment / reward system, and we know that that kind of system results with an intelligent behavior, than we can label entire evolution as an intelligent process. We talked about this a while ago, but I'm bringing some new conclusions.
-
I don't really get the punishment factor of the end of an evolutionary chain. It's just something that didn't work out isn't it ?
-
I imagine having no kids as a punishment. No genes are passed to the next generations to be mixed up with each other.
-
It doesn't seem like a punishment. I'd need to know the final conclusion to know for sure though...
-
I have in mind this kind of analogy
1. With thought process an idea gets born:- If it does what is expected -> as a reward, the idea gets memorized
- if it doesn't fit the reality -> as a punishment, the idea gets forgotten
All the successful ideas form an intelligent system that improves over time
2. With evolution a kid gets born:- if it succeeds to reproduce -> as a reward, its genes continue to pass to the next generations
- if it fails to reproduce -> as a punishment, its genes are being cut out of the next generations
All the newborn generations form an intelligent system that improves over cycles.
So the entire evolution looks like a thought process to me
-
Success and failure, reward and punishment, these don't seem like terms that are applicable to a completely inanimate and unconscious process. Life came about because molecules that self replicate are more likely to stick around than molecules that don't. Molecules that self-replicate even better are even more likely to stick around. Molecules that think they will burn in hell if they don't do their utmost to stick around are most likely of all to stick around.
-
I think it's a fuzzy area :D
I think it's just the way I perceive the word punishment. I can see where you are coming from Ivan :)
-
Sorry about taking this a little off topic, it was a well presented video and easy to understand - I found it interesting that the learning transferred from a software simulation to hardware. No one tell Lock ;)
Hmm, I was thinking, evolution can almost come to a full stop - because the fossil record shows us that some animals have remained the same for millions of years.
So it seems that once a solution is good enough to ensure survival then evolution stops or pauses. This fits with Ivan's analogy - the reward is continued life, the 'punishment' is no more life from that ancestor.
This robot seeks it's rewards and becomes something useful. How to say it is rewarded, not sure. Perhaps my human perspective is getting in the way.
:detective:
-
No one tell Lock ;)
When I posted this I figured he'd be first to reply and all over the thread like a rash. Let's just hope he's absent because he's outside getting some fresh air and exercise.
Hmm, I was thinking, evolution can almost come to a full stop - because the fossil record shows us that some animals have remained the same for millions of years. So it seems that once a solution is good enough to ensure survival then evolution stops or pauses. This fits with Ivan's analogy - the reward is continued life, the 'punishment' is no more life from that ancestor.
That got me thinking. Crocodiles are one of the best examples of this. They've been around unchanged for about 200 million years and they seem to be in little danger of going away any time soon.
https://www.thenakedscientists.com/articles/questions/why-havent-crocodiles-changed
Those two answers a) because they're so successful and b) because nothing else wants their niche, don't seem very satisfactory to me. I would phrase it this way: the niche they occupy has been available unchanged for 200 million years. In that time there have been several extinction level events, Pangaea has broken up to form the continents, and the very composition of the atmosphere has changed, but crocodiles are still there in the same form.
That's because there have always been muddy riverbanks and all the other animals, no matter what form they take, have to come down to drink twice a day. Most other habitats have disappeared and come back again several times over.
-
the niche they occupy has been available unchanged for 200 million years
This. Yes, some life forms are going to have a hard time evolving fast enough to cope with a quickly changing environment. Like with those mass extinctions you mention, I'm immediately thinking of Ammonites and things; which were plentiful and had a massive environment they could thrive in. But when things went awry failed to cope.
I guess the Crocs got lucky - right time right place.
-
I feel like I remember reading an article once that compared evolution to a learning process, and noted that it's a bad/inefficient learning process ... if only because it has no memory. If some combination of genes proves to be a poor adaptation and dies out, there's nothing to prevent that combination from being "tried" again, if it happens to fall out of the genetic RNG a second time. In other words, evolution preserves its successes but doesn't learn from its mistakes.
-
If you have to pick randomly twice an element out of infinite set, what are the odds to pick the same element?
But on the other hand, I would be thrilled if Down's syndrome was more rare condition.
-
I feel like I remember reading an article once that compared evolution to a learning process, and noted that it's a bad/inefficient learning process ... if only because it has no memory. If some combination of genes proves to be a poor adaptation and dies out, there's nothing to prevent that combination from being "tried" again, if it happens to fall out of the genetic RNG a second time. In other words, evolution preserves its successes but doesn't learn from its mistakes.
Is it so inefficient when you consider the amount of time involved though ?
And say the first branch failed due to lack of success in the environment, but a later branch (although the same) in a changed environment may work out better. So what I am saying is that it depends a lot on the environment for how well the mechanism works.
If you have to pick randomly twice an element out of infinite set, what are the odds to pick the same element?
But on the other hand, I would be thrilled if Down's syndrome was more rare condition.
Wouldn't the chance be one in infinity ? But wouldn't there be limited possibilities for evolutionary branches ? I mean an ant doesn't suddenly grow an elephant's trunk. It has to be capable of doing it.
-
I have to admit, evolution doesn't pick from infinite set. One extreme is that a kid is exact copy of kid's only parent - in asexual reproduction (some snails can do that). In sexual reproduction it is a combination of parent genes - some deviation of parent genes in a certain degree.
But given that there is relatively low number of different genetic disorders, those disorders are pretty common (a few percents) along human species. Of all disorders our sick minds could imagine, the nature picks up just some few dozens of them. How to explain that? Could it be that some parents are simply not compatible? Or maybe it is an one parent deal? Or it has something to do with parents being family related? And why family related parents can't have healthy kids?
But it would be awesome if the nature would somehow learn from its mistakes too.
[Edit]
Thinking about mother nature mistakes... Who is to tell that some living being is a mistake? Call me naive, but I think that nature is has a gentle soul. It doesn't call anyone a mistake to dismiss him from evolutionary line. It gives us all a chance over and over again, until we make up to succeed in our environment. I find it very gentle and romantic.
-
But it would be awesome if the nature would somehow learn from its mistakes too.
Genes are something like a memory though aren't they ?
Biology is not a strong area of knowledge for me, I only really studied it at school for a couple of years. I do see that people like the Nepalese living in high mountains have different genes that help them deal with the higher altitude. They will still suffer altitude sickness some times though, but are generally hardier than most in that respect I have learnt.
The way I see it, nature is both kind and hostile. When Darwin's Theory of Evolution came about many people just didn't like how unforgiving nature was when laid out that way. Probably many still feel the same way.
-
After a bit of googling I learned that all living things from bacteria to humans have about five hundred genes in common out of about one hundred thousand different possible genes. Human beings have about twenty thousand genes.
Now the interesting thing is that not all of our genes are actually expressed in any given organism. Most of them have no effect. A few decades ago it was thought they were redundant and for a while they were referred to as "junk DNA". In fact they're all there waiting until they're needed. Evolution doesn't throw out genes just because they're not needed for a while.
The actual genes that are expressed are selected by RNA which is created in the parent organism during its life and is influenced by environmental conditions. In this way, when the environment changes, organisms don't have to evolve lost characteristics all over again, because many of them were already stored in the library of genes carried by the parents.
-
Ahh, we were heading in the right direction then :)