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

Show HN: Unity 3d Neuroevolution Flappy Bird

github.com

Post reply on HN
Print view View original

11–17 of 17 posts

Re: Show HN: Unity 3d Neuroevolution Flappy Bird

#11

Post by tunetine »

mrspeaker wrote: post #9

Why is there only ever one (sometimes two/three) decent players every generation? Most will end up dying after one or two poles... how come once the algorithm gets decent there are many more making through the game along with the best one? (Also, I'd like "number of taps per game segment" be a weight... fall until the very last second then a couple of quick taps - none of this "spamming to keep level" stuff: where's…

It seems like half fall below and/or above the screen limits every round. I may be incorrect but you would think evolution after a round or two would take care of that type of issue.

Re: Show HN: Unity 3d Neuroevolution Flappy Bird

#12

Post by indescions_2017 »

The Asteroids demo is cool too:

https://xviniette.github.io/AsteroidsLearning/

AI Lab at UTexas Austin has more Atari 2600 NEAT demos as well. The Kung Fu Master "button masher" style makes me think a Street Fighter V agent would be hilarious to see in Human vs AI competitive action!

http://www.cs.utexas.edu/~ai-lab/?atari

For a proof of concept, this shows the capability of ML in a web browser. Creating an ad hoc cluster of a hundred webrtc peers would yield a formidable (but slow) meta learner. And just to put it in perspective: sentient.ai's petascale darkcycle cluster consists of ~1M CPUs and ~1k GPUs:

https://www.sentient.ai/platform/scale/

Distributed computation seems to give natural evolution a competitive advantage: it is by design already parallel.

Reference for further study: Evolving Deep Neural Networks

https://arxiv.org/pdf/1703.00548.pdf

Re: Show HN: Unity 3d Neuroevolution Flappy Bird

#14

Post by galleanv »

Rathmatik wrote: post #4

This is pretty awesome. I am curious though, does this in any way use the same algorithm as the project that inspired this ( https://xviniette.github.io/FlappyLearning/ ). That one appears to be vastly quicker at learning (reached over 13 million and counting at generation 18).

I think that environment in Unity version is more complex, it uses "real" physics (box2d) to simulate the world. JS version use very simple collision detection. But I am not 100% sure (this is my beginning in AI world)

Re: Show HN: Unity 3d Neuroevolution Flappy Bird

#15

Post by galleanv »

mrspeaker wrote: post #9

Why is there only ever one (sometimes two/three) decent players every generation? Most will end up dying after one or two poles... how come once the algorithm gets decent there are many more making through the game along with the best one? (Also, I'd like "number of taps per game segment" be a weight... fall until the very last second then a couple of quick taps - none of this "spamming to keep level" stuff: where's…

I am beginner in all of this and also I would like to know why this is happening. In this example every generation have 20 new genomes (birds), 3 best stay from previous generation (elitism), rest are effect of mutation. Maybe mutation rate/range have to be tweaked. Current solution is best what I found so far.
Post reply on HN