Applying AI to games: the Q-Learning algorithm

#1

Post by nrox » Mon, Sep 16, 2013, 10:05 PM UTC

Applying AI to games: the Q-Learning algorithm
nrox.github.io

Re: Applying AI to games: the Q-Learning algorithm

#2

Post by mtinkerhess » Mon, Sep 16, 2013, 10:53 PM UTC

For a more in-depth introduction to reinforcement learning, Sutton and Barto's book is available online:

http://webdocs.cs.ualberta.ca/~sutton/book/ebook/the-book.ht...

Re: Applying AI to games: the Q-Learning algorithm

#3

Post by guiambros » Tue, Sep 17, 2013, 4:07 AM UTC

mtinkerhess wrote: post #2

For a more in-depth introduction to reinforcement learning, Sutton and Barto's book is available online: http://webdocs.cs.ualberta.ca/~sutton/book/ebook/the-book.ht...

Thanks, this is great! More specifically, there's a (draft) version of the second edition in PDF format, which is a much easier to read than the HTML format. Link here [1], on the very bottom.

[1] http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html

Re: Applying AI to games: the Q-Learning algorithm

#4

Post by nrox » Tue, Sep 17, 2013, 11:56 AM UTC

mtinkerhess wrote: post #2

For a more in-depth introduction to reinforcement learning, Sutton and Barto's book is available online: http://webdocs.cs.ualberta.ca/~sutton/book/ebook/the-book.ht...

The book is great. The problem with AI books and many technical books has to do with their huge size. The optimal instruction to learn AI for basic usage would be: provide an half page explanation and some working, tweakable examples.