MarI/O – Machine Learning for Video Games
youtube.com
MarI/O – Machine Learning for Video Games
1–10 of 20 posts
Re: MarI/O – Machine Learning for Video Games
#2For interested people, here is an interview with K. Stanley, the author of NEAT: http://aigamedev.com/open/interviews/galactic-arms-race/
I was wondering if this learning technique was applied to any other games. I came across this:
1. https://www.cs.utexas.edu/~mhauskn/papers/atari.pdf
2. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.93....
Re: MarI/O – Machine Learning for Video Games
#3A very cool demonstration showing how the network evolves.
Re: MarI/O – Machine Learning for Video Games
#4Re: MarI/O – Machine Learning for Video Games
#5I have reasonable suspicion that it wouldn't be nearly as easy to train without "spinning" move which basically gives invulnerability against all enemies sans their bullets, iirc.
The main problem I see is that the algorithm is learning from the same level (or set of levels). It would be interesting to see what happens if you give it some completely new level to play.
Re: MarI/O – Machine Learning for Video Games
#6I have reasonable suspicion that it wouldn't be nearly as easy to train without "spinning" move which basically gives invulnerability against all enemies sans their bullets, iirc.
Re: MarI/O – Machine Learning for Video Games
#7I have reasonable suspicion that it wouldn't be nearly as easy to train without "spinning" move which basically gives invulnerability against all enemies sans their bullets, iirc.
Re: MarI/O – Machine Learning for Video Games
#8Re: MarI/O – Machine Learning for Video Games
#9Re: MarI/O – Machine Learning for Video Games
#10I have reasonable suspicion that it wouldn't be nearly as easy to train without "spinning" move which basically gives invulnerability against all enemies sans their bullets, iirc.
Wait, does it really give you invulnerability? In the video Mario never runs into a single enemy while spin jumping.