Timeline for Viable use of genetic algorithms to train neural nets in a poker bot?
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 8, 2017 at 1:14 | answer | added | D.W.♦ | timeline score: 1 | |
| Oct 7, 2017 at 11:07 | comment | added | Raphael | I use "magic" here to express that you (we) don't really know when and why it works (well), anyway. | |
| Oct 7, 2017 at 10:57 | comment | added | Kody Puebla | So I should just try it and hope for the best since there's no way to tell? Also, do you consider this a magic model because so much is reliant on the NNs? | |
| Oct 7, 2017 at 10:28 | comment | added | Raphael | This seems like an open-ended tinkering prompt, i.e. not a question that can be answered concisely and comprehensively. I think it's therefore too broad (or unclear?) for this platform; community votes, please! | |
| Oct 7, 2017 at 10:27 | comment | added | Raphael | Sure, you can train one "magic" model using a "magic" technique. Any NN you get out is "viable". There's just no telling how good it'll be. | |
| Oct 7, 2017 at 10:26 | history | edited | Raphael |
edited tags
|
|
| Oct 7, 2017 at 5:00 | review | First posts | |||
| Oct 7, 2017 at 16:12 | |||||
| Oct 7, 2017 at 5:00 | history | asked | Kody Puebla | CC BY-SA 3.0 |