Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Thanks - thinking of putting up a version that has not been pretrained, so users can see the training over several generations. I think I have one lying around - remind me on twitter if I forget.

I'm also trying to learn 'deep q learning' (q-learning with a neural net as the q function) and other cool stuff that has recently been developed.

btw, I think your previous post with the 'brain' of 140 numbers is messing up this thread a bit on my browser for some reason and the comments not wrap, wonder if there's a way to fix it.



Many Thanks for the untrained version - I am working on visualising the evolving genome based on your RGBA illustration.

I read Sutton and Barto on Q-Learning but only 'got' it when I saw it hand-done with matrix math. http://mnemstudio.org/path-finding-q-learning-tutorial.htm

Sutton & Barto suggest Eligibility Traces seem necessary to make Q learn fast enough. http://webdocs.cs.ualberta.ca/~sutton/book/ebook/node79.html

Gomez's thesis suggests that genetic methods have an advantage over backprop for learning sequences of actions. http://www.cs.utexas.edu/users/nn/downloads/papers/gomez.phd...

Deep Q Learning is brilliant - evolving the Q function would certainly be very interesting - currently trying to get the ALE sending frames to my convnet :)

mods have helped fix the errant brain code - thanks for the heads up.


cool! Let's talk further offline later- I would be interested to know what you end up doing with it, and pick your (biological) brain for ideas. Ping me on Twitter message later-




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: