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

NeuroEvolution – Flappy Bird

xviniette.github.io

Post reply on HN
Print view View original

31–40 of 103 posts

Re: NeuroEvolution – Flappy Bird

#31

Post by maaaats »

fenomas wrote: post #26
gioele wrote: post #25

Interestingly, the updates are done on the basis of only 2 external inputs [1]: the height of the bird in the screen and height of the aperture in the next pipe. Using only these two parameters the neural network decides whether to flap or not. I would had expected at least also the horizontal distance from the next pipe... [1] https://github.com/xviniette/FlappyLearning/blob/gh-pages/ga...

Wow, that's really unexpected. This isn't my field, but given the simplicity of the inputs and network, and the way commenters are seeing the demo achieve perfect play after anything between 2 and 200 generations, it makes me wonder if this isn't more of a brute-force search than actual learning? That is, it smells like there's a "correct" set of neuron values - where any genome within some tolerance of those values…

"All" evolutionary algorithms are basically a local search with smart heuristics. Where a local search is a brute-force where you move in small directions based on feedback on where you are in the solution space.

Re: NeuroEvolution – Flappy Bird

#32

Post by arcatek »

JoshTriplett wrote: post #7

At 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,…

Gen 17 had its last bird run forever

Re: NeuroEvolution – Flappy Bird

#33

Post by manmal »

JoshTriplett wrote: post #7

At 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,…

57 for me.

Re: NeuroEvolution – Flappy Bird

#34

Post by hayksaakian »

JoshTriplett wrote: post #7

At 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,…

gen 6 seems to have gotten it right for me, still running, ill follow back when it loses edit: still running at 4600+ 5 minutes later on gen 6

Re: NeuroEvolution – Flappy Bird

#36

Post by lloeki »

JoshTriplett wrote: post #7

At 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,…

gen 9, lots of close calls, but still flying fine

Re: NeuroEvolution – Flappy Bird

#38

Post by simcop2387 »

JoshTriplett wrote: post #7

At 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,…

What's interesting is I've run it several times now, and I've gotten the perfect bird about half the time on an early generation (<10), but sometimes it just doesn't want to find it for a while. I'm wondering if the net is just at the threshold of being the minimal set of neurons that are needed for it to be able to get it so easily by random chance.

Re: NeuroEvolution – Flappy Bird

#39

Post by w23j »

This is one of these fantastic "all that is done with so little code?!" moments.

Amazing that this can be done in 300 lines of perfectly readable JS without any libraries. And the author apparently wrote it in 2 days. Great intro to genetic algorithms and reinforcement learning. Universities should teach like that.

Edit: Somebody has asked about the big picture how the thing works:

You use a neuronal network to decide at each step to flap the birds wings or not. That is the only output. The input is only the birds height (y-position) and the height of the next hole. (https://en.wikipedia.org/wiki/Feedforward_neural_network)

The question now is how to find the correct weights for the net.

That net is not trained in a traditional supervised way like with gradient descent (which would be more complicated). Instead it uses a genetic algorithms to find new weights for neuronal networks of future generations. That is use some of the best individuals. Some randomly generated ones and some created by breeding from existing individuals. (https://en.wikipedia.org/wiki/Genetic_algorithm)

And that's basically it in this case.

Re: NeuroEvolution – Flappy Bird

#40

Post by onion2k »

gioele wrote: post #25

Interestingly, the updates are done on the basis of only 2 external inputs [1]: the height of the bird in the screen and height of the aperture in the next pipe. Using only these two parameters the neural network decides whether to flap or not. I would had expected at least also the horizontal distance from the next pipe... [1] https://github.com/xviniette/FlappyLearning/blob/gh-pages/ga...

The pipes are evenly spaced so horizontal distance just goes away.
Post reply on HN