As somebody who's never looked into this kind of task before, I couldn't believe it was powered by a ~300 line file and not some massive library.
Really awesome.
NeuroEvolution – Flappy Bird
11–20 of 103 posts
Re: NeuroEvolution – Flappy Bird
#12At generation 83, a single bird emerged that successfully navigated through several hundred columns (current score 100000+) and showed no signs of failing. It took a few dozen generations to find versions that would make it through a few columns if those columns had gaps without too much vertical distance between them. Somewhere in generation 60-70, I could see versions figuring out how to transition between heights,…
53 for me. The previous generations didn't even look close then all of a sudden this one.
Re: NeuroEvolution – Flappy Bird
#13Can this be used on, say, Mario Bros?
Re: NeuroEvolution – Flappy Bird
#14At generation 83, a single bird emerged that successfully navigated through several hundred columns (current score 100000+) and showed no signs of failing. It took a few dozen generations to find versions that would make it through a few columns if those columns had gaps without too much vertical distance between them. Somewhere in generation 60-70, I could see versions figuring out how to transition between heights,…
53 for me. The previous generations didn't even look close then all of a sudden this one.
Same. Mine is on generation 22 and is the first one to get past even 30 seconds. So far no sign of stopping.
edit: Gen 22 still going strong @ 1 bird, up to 231,000 points. Looking at game.js it's a fairly simple model, I suspect once you get a bird that makes it past the 1-minute mark it will be able to continue forever.
Re: NeuroEvolution – Flappy Bird
#15Can anyone give me insight on where the code learning is? I cloned the repository and after a quick glance I don't see where the "meat" is.
It is a using a genetic algorithm so learning lies in the mutation and crossover of chromosomes as well as selection of the fittest individuals. https://github.com/xviniette/FlappyLearning/blob/gh-pages/Ne...
It's also using a simple neural network, which is the target of the genetic algorithm, if I understood it right. I haven't seen this combination often - does that make sense in general, or is this just interesting as in playing around with those concepts?
Re: NeuroEvolution – Flappy Bird
#16This is really cool! I am at generation 17 and it shows already no signs of failing.
Re: NeuroEvolution – Flappy Bird
#17Generation 48. What about you guys?
Generation 10, which was weird, but got to 70k points before I closed it. I wonder why mine was so much lower, sheer luck?
Re: NeuroEvolution – Flappy Bird
#18Generation 48. What about you guys?
Generation 12. 12k+ http://imgur.com/a/PtvLI
Re: NeuroEvolution – Flappy Bird
#19Earlier quoted context omitted.
It is a using a genetic algorithm so learning lies in the mutation and crossover of chromosomes as well as selection of the fittest individuals. https://github.com/xviniette/FlappyLearning/blob/gh-pages/Ne...
It's also using a simple neural network, which is the target of the genetic algorithm, if I understood it right. I haven't seen this combination often - does that make sense in general, or is this just interesting as in playing around with those concepts?
In a way that's what nature does :) I think this combination is quite common.
While visiting a lab in Paris, I saw some researchers using neuroevolution to teach a bird-like robot how to fly.
some links related to neuroevolution:
https://en.wikipedia.org/wiki/Neuroevolution_of_augmenting_t...
Re: NeuroEvolution – Flappy Bird
#20Can this be used on, say, Mario Bros?
You mean this script? Or machine learning in general? If the later then it has already been done: https://www.youtube.com/watch?v=qv6UVOQ0F44 (great educational video)