Infinite Mario AI - Long Level
Channel:Robin Baumgarten · Length:1:11 · Published:2009-08-05 · Views:1264987
Summary
A bot built by Robin Baumgarten plays Infinite Mario using A* path-finding, shown as a red planned path that updates as new obstacles appear. It won the Mario AI competitions and uses only on-screen information.
Why HN recommends it
HN points to it as a vivid demo that plain A* search can beat fancier machine-learning approaches in game AI.
It's pretty interesting, a lot of people wrote/are writing high falutin' machine learning algorithms — HN, 2011
Machine learning & deep learning · Algorithms & data structures · Chess, board games & puzzles
Subtitles (excerpt)
anywhere [hudba] you go Anything you do any All It's all [hudba] Back to you tell me What did I get Myself into [hudba] Surprise that I need you [hudba] every time I think about soct I can't [hudba] don't know what to do All The Time I'm giving Something [hudba] taking Nothing Why Should I Leave It Up To You [hudba] [zpěv] [zpěv] [hudba] It Up To You Up To [hudba] You
On Hacker News
The original java infinite mario was used in the fascinating Mario AI competition. Details and papers here: [LINK] Video of last years winning entry at work here: [VIDEO] It's pretty interesting, a lot of people wrote/are writing high falutin' machine learning algorithms, but they are consistently trounced by good old A* techniques. — JonnieCache, 2011-07
Reminds me of the AI competition on infinite mario, recently: Here is a video of the winning bot (A* based approach), cool to watch, as they display its trajectory calculations. [VIDEO] GA is cool and everything, but I am sometimes sceptical about its merits. Yes, it gives you a natural problem representation, but would it really have done a better job in this particular domain than using a techn… — feral, 2010-11
If you are impressed with this one follow the link in the video to here: [VIDEO] For all my hours as a kid I was never this good, I never even realized I could kill the pipe fish by jumping from below. — Radix, 2009-08
There was even an Infinite Mario AI contest in which you had to write a player which gets through as many levels of increasing difficulty as possible. The winning solution? A* of course: [VIDEO] (I had an also-ran entry in this contest that took 3rd place, but my solution wasn't significantly different than Robin's -- his was able to anticipate bullets firing but mine wasn't) Writeup: [LINK] — a1k0n, 2012-09
I seem to miss such contests most of the time and only hear about them when they ended. I would love to attend to some, just for the fun (because I don't know if I would have any chance to actually win). Where would be a good source for such competitions? Another fun competition I read about was the Super Mario AI competition in 2009 where the winner has succeeded with an A* algorithm which he pr… — albertzeyer, 2010-08
Related videos
- Keep your goals to yourself | Derek Sivers · TED · 3:46
- Tech Talk: Linus Torvalds on git · Google · 1:10:15
- BlackHat USA 2011: SSL And The Future Of Authenticity · Christiaan008 · 48:01
- Playing to Lose: AI and "Civilization" (Soren Johnson) · Google TechTalks · 1:00:28
- The Loving Trap · Ben Woodhams · 2:58
- 27C3: Adventures in analyzing Stuxnet (Bruce Dang from Microsoft) · basti0007 · 1:14:56
- Hans Rosling: Debunking third-world myths with the best stats you've ever seen · TED · 20:36
- 28c3: Print Me If You Dare · 28c3 · 1:03:36
- Super Mario World Credits Warp Explained · Frieze · 11:54
- The spelled-out intro to neural networks and backpropagation: building micrograd · Andrej Karpathy · 2:25:52
- But what is a neural network? | Deep learning chapter 1 · 3Blue1Brown · 18:40
- AlphaGo - The Movie | Full award-winning documentary · Google DeepMind · 1:30:28
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 · 3Blue1Brown · 27:14
- USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible? · USENIX · 51:22
- CppCon 2017: Matt Kulukundis “Designing a Fast, Efficient, Cache-friendly Hash Table, Step by Step” · CppCon · 59:33
- Lecture 1 | Machine Learning (Stanford) · Stanford · 1:08:40