Evolving AI Plays Super Mario

  • Thread starter Drakkith
  • Start date
  • #1
Drakkith
Staff Emeritus
Science Advisor
22,070
6,149
Here's a neat video I found of an evolving AI that plays the video game Super Mario. The AI is based off of something called NEAT, or Neuro Evolution of Augmenting Topologies (paper here), and was programmed in Lua (source code here). I thought it was pretty cool, so I just figured I'd share.

 
  • Like
Likes Hoophy, mister mishka, collinsmark and 5 others

Answers and Replies

  • #2
Borg
Science Advisor
Gold Member
2,049
3,306
It's fascinating how artifical learning algorithms are advancing.
 
  • #3
Drakkith
Staff Emeritus
Science Advisor
22,070
6,149
It's fascinating how artifical learning algorithms are advancing.

Indeed. I actually created a really simple simulation of some evolving cells about a year ago, but it was nothing like this. There was no learning involved, the cells just adapted over time without any "intelligence".
 
  • #4
Borg
Science Advisor
Gold Member
2,049
3,306
This month's Scientific American happens to have several articles on AI. It also refers to neural networks similar to what is mentioned in the video.
 
  • #6
Hornbein
1,060
735
I've heard that numerous games are played successfully this way. It was a key step on the way to the Go championship.
 
  • #7
Drakkith
Staff Emeritus
Science Advisor
22,070
6,149
I've heard that numerous games are played successfully this way. It was a key step on the way to the Go championship.

The "Go" championship?
 
  • #8
Ygggdrasil
Science Advisor
Insights Author
Gold Member
2021 Award
3,522
4,179
The "Go" championship?

Earlier this year, an algorithm designed by Google defeated the top-rated Go player in the world. Go is an ancient Chinese board game which has simple rules, but is very complex because of the number of possible moves (there are many more possible games of Go than there are of chess, for example).
In the final game of their historic match, Google’s artificially intelligent Go-playing computer system has defeated Korean grandmaster Lee Sedol, finishing the best-of-five series with four wins and one loss.
http://www.wired.com/2016/03/googles-ai-wins-fifth-final-game-go-genius-lee-sedol/

Here's a link to the academic paper on the algorithm: http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html
 
Last edited by a moderator:
  • #9
collinsmark
Homework Helper
Gold Member
3,212
2,032
Several times I've created Artificial Neural Networks (ANN) for fun and kicks (various languages: Matlab, C++ and C#). Thus far they were only more conventional feed-forward networks that were trained using back-propagation with well defined training sets.

I think this NEAT algorithm might be quite useful for applications where well defined training sets are not practical.
 
  • #10
Hornbein
1,060
735
I did not think Go would be solved in my lifetime. It was an epoch-making event, IMO.
 

Suggested for: Evolving AI Plays Super Mario

  • Last Post
Replies
5
Views
468
Replies
1
Views
427
  • Last Post
Replies
24
Views
2K
Replies
5
Views
1K
  • Last Post
Replies
1
Views
729
  • Last Post
Replies
6
Views
993
Replies
97
Views
7K
Top