Difference between revisions of "Thread:Talk:Diamond/Version History/gun tuning tangent/reply (26)"

From Robowiki
Jump to navigation Jump to search
(Reply to gun tuning tangent)
 
(No difference)

Latest revision as of 21:31, 15 July 2012

Having a classifier which differentiates both patterns solves the problem (distance to corners against Walls).

If not, making many k-NN searches with k=1 gives you 30% of the ticks from one pattern and 70% of the ticks from the other pattern, and the resulting pattern is a 30%/70% mix of the two. It assumes a 3rd unseen pattern can be predicted from 2 previous patterns.

Should perform well against orbital movement, where turn rate changes gradually with distance and a 3rd unseen turn rate (or a zig-zag) can be predicted from 2 others. But perform bad against pattern movement, where patterns don't change gradually with classifiers.