Using previous GFs as dimensions

Jump to navigation Jump to search

Interesting. I think you should definitely test against RM, because surfers generally don't like anything with bullet waves, and simple movers are pretty easy to hit. Also, you might want to start with the basics (distance, velocity, relative heading, acceleration...) before you get into data decay and experimental dimensions. Good luck.

Sheldor (talk)04:42, 20 December 2013

Don't worry! I am actively optimizing my more "normal" gun using standard predictors. What bots would you recommend as good test bots with strong RM? Tmservo its just a 6 dimensional KNN, 5 are lastGFs normalized to 0-1, last one is sqrt(shots)* .5. I haven't added any kernel density stuff to this tree, I plan to try that.

Straw (talk)06:35, 20 December 2013

just drussgt, diamond, gilgalad, tomcat, xandercat, waveserpent, nene, gressuffurd,

Tmservo (talk)13:21, 20 December 2013

Those are not bots with Random Movement as Straw asked for.

Rednaxela (talk)14:45, 20 December 2013
 

I'd suggest you use the reference bots from the Targeting Challenge RM, because they give you a good variety of random movements, and have been thoroughly tested against before, so the 'expected' result is fairly accurately known. You may wish to use RoboRunner to automate testing against that set as well.

Rednaxela (talk)14:47, 20 December 2013
 

Yeah, like Rednaxela said, the reference bots would work well. I'm curious, are you planning to have these two guns in a VG array, or are you just experimenting in parallel?

Sheldor (talk)15:30, 20 December 2013

Not sure yet, could use a VG array, or might get results from two trees and do density calculations on the results from both.

Straw (talk)03:11, 21 December 2013