http://robowiki.net/w/index.php?title=Thread:Talk:Rolling_Averages/Rolling_KD-Tree%3F/reply&feed=atom&action=historyThread:Talk:Rolling Averages/Rolling KD-Tree?/reply - Revision history2024-03-29T02:21:23ZRevision history for this page on the wikiMediaWiki 1.34.1http://robowiki.net/w/index.php?title=Thread:Talk:Rolling_Averages/Rolling_KD-Tree%3F/reply&diff=56956&oldid=prevKev: Reply to Rolling KD-Tree?2021-08-07T18:06:27Z<p>Reply to <a href="/wiki/Thread:Talk:Rolling_Averages/Rolling_KD-Tree%3F" title="Thread:Talk:Rolling Averages/Rolling KD-Tree?">Rolling KD-Tree?</a></p>
<p><b>New page</b></p><div>I've seen several ways of making DC models favor recent data points: <br />
# As you say, add time as a feature to the data points. [[BeepBoop]] and [[DrussGT]] do this. I'm not sure if it is an advantage or disadvantage having time "compete" with other dimensions instead of it being a separate criteria for selecting points.<br />
# Give your KD-Tree a maximum size where older data points are deleted as new ones are added. For example [[Diamond]]'s anti-surfer gun combines several KD trees with different max sizes to find the closest matches in the last 125, 400, 1500, and 4000 waves. This of course also makes your tree(s) faster!<br />
# Have the values in your tree store the time as well as the guessfactor. Then sort your top k matches by their age and weight them according to their rank. [[Diamond]] does this for its surfing, but not its guns. I suppose instead of ranking them, you could also weight them by 0.99^age or something, but I haven't seen that done before.<br />
They each have different advantages/disadvantages and I'm sure there are other things you could try as well!</div>Kev