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

Hacking Flappy Bird with Machine Learning

sarvagyavaish.github.io

Post reply on HN
Print view View original

51–56 of 56 posts

Re: Hacking Flappy Bird with Machine Learning

#51

Post by habosa »

hugs wrote: post #41
iqster wrote: post #18

Earlier quoted context omitted.

Someone made a robot that played Angry Birds: https://us.pycon.org/2012/schedule/presentation/470/ I was wondering if this would work for Flappy birds. Due to the speed of the game, I think it is going to be quite a challenge. P.S. If you are interested in the mindstorms robot part, I'll put a shameless plug for a robot I built some time ago (based on some work by David Singleton). Code is on github but here is a pyc…

Ohai! (I presented that Angry Birds bot at PyCon.) My bot is now called "Tapster" and I continue to make improvements. It's completely open-source; I'd love to expand the community of game-playing bot fans. ( http://tapsterbot.com ) I even created a 3d-printable LEGO Technic-compatible building material to make the bot. ( http://bitbeam.org ) I'm working on training Tapster to play Flappy Bird. I'm going down the rou…

This is why I love Hacker News, I can ask a question about getting a lego robot to beat my favorite cell phone game and there's someone watching who has done it.

Would love to hear how it goes! I'm sure a blog post about that would be front page HN material.

Re: Hacking Flappy Bird with Machine Learning

#52

Post by habosa »

nanidin wrote: post #40
habosa wrote: post #14

I really want to build a Lego Mindstorms robot (or similar) that watches my phone with a webcam, holds a stylus, and plays Flappy Bird. I have played enough (high score 194) that I am pretty sure I know the right strategy, I just want to take human error out of the equation. Are there open source vision libraries that are low-latency enough to play this in real time? Assuming the robot could keep up with some regular…

If you're going to go as far as running it in an emulator... then why not just write something that works in process and avoids the whole visual feedback / physical input loop altogether? It's how bots are written for MMO's like WOW.

I'd like to do it without altering the app, which makes it more like the robot is playing the game not cheating it. This limits me to processing the game's output in real time.

Re: Hacking Flappy Bird with Machine Learning

#53

Post by tripzilch »

potash wrote: post #28

How hard would it be to solve this deterministically? Can someone comment on the game's physics? I am assuming: - constant horizontal velocity - gravity - flapping implemented via impulse - collisions are handled with bounding boxes Maybe someone who knows something about optimal control (ODE) say whether this is analytically solvable? Of course there's still the practical stuff (numerical integration, I/O lag) to de…

In another Flappy Bird thread (the MMO one), somebody posted this formula:

    Let distance between ground and top of screen=100. 
    Bird position after a flap at y=y0, time=t0:
    y(t) = y0 + 13.8 - 147 * (t - t0 - 0.288)^2
(https://news.ycombinator.com/item?id=7229018 -- note the original comment had "+ 0.288", but if you plot the graph this was obviously a mistake)

I tried it out in my own HTML5/JS Flappy clone (mine's not at all interesting or even done, but I felt I had to give it a try), and the movement seems really accurate.

I have no idea how they got to those numbers, however.

Re: Hacking Flappy Bird with Machine Learning

#54

Post by pilooch »

Reinforcement learning (RL) is the future of real-world AI. Bear my words ;) RL has been around for a long time, it is the mix of optimal (in the optimization sense) decision making along with machine learning (ML). It does benefit of most recent advances in ML. As such it is likely to power the next batch of 'intelligent' applications and services.

Re: Hacking Flappy Bird with Machine Learning

#55

Post by grogenaut »

iqster wrote: post #18
habosa wrote: post #14

I really want to build a Lego Mindstorms robot (or similar) that watches my phone with a webcam, holds a stylus, and plays Flappy Bird. I have played enough (high score 194) that I am pretty sure I know the right strategy, I just want to take human error out of the equation. Are there open source vision libraries that are low-latency enough to play this in real time? Assuming the robot could keep up with some regular…

Someone made a robot that played Angry Birds: https://us.pycon.org/2012/schedule/presentation/470/ I was wondering if this would work for Flappy birds. Due to the speed of the game, I think it is going to be quite a challenge. P.S. If you are interested in the mindstorms robot part, I'll put a shameless plug for a robot I built some time ago (based on some work by David Singleton). Code is on github but here is a pyc…

yes, because if there's one thing that computers are known for... it's being slow.

Re: Hacking Flappy Bird with Machine Learning

#56

Post by Shuai »

habosa wrote: post #14

I really want to build a Lego Mindstorms robot (or similar) that watches my phone with a webcam, holds a stylus, and plays Flappy Bird. I have played enough (high score 194) that I am pretty sure I know the right strategy, I just want to take human error out of the equation. Are there open source vision libraries that are low-latency enough to play this in real time? Assuming the robot could keep up with some regular…

http://www.cloudteastudio.com/bird.html Another group already done it. check it out
Post reply on HN