Difference between revisions of "Elo Rating"
Jump to navigation
Jump to search
(initial commit) |
m (fix) |
||
Line 1: | Line 1: | ||
{{Stub}} | {{Stub}} | ||
+ | {{cleanup}} | ||
Pasted from page [[Darkcanuck/RRServer/Ratings]] | Pasted from page [[Darkcanuck/RRServer/Ratings]] |
Latest revision as of 06:24, 14 October 2017
This article is a stub. You can help RoboWiki by expanding it. |
This article may require cleanup to meet RoboWiki's quality standards. Please improve this article if you can.
|
Pasted from page Darkcanuck/RRServer/Ratings
- New competitors start at a rating of 1600
- The expected % score outcome of a pairing between bots A and B is given by E(A,B) = 1.0 / (1 + 20^(ratingA-ratingB)/800))
- When a new pairing result is submitted to the server:
- The new % score for bot A vs bot B
New(A,B) = scoreA / (scoreA + scoreB)
- The running pairing score of A vs B
Pair(A,B)' = 0.7 * Pair(A,B) + 0.3 * New(A,B)
- Then calculate the rating change for A by iterating over all ranked bots Ri:
deltaRatingA += 3.0 * (Pair(A,Ri) - E(A,Ri)
- Do the same for B
- Update the ratings for A and B by adding the new delta to their current rating.
- The new % score for bot A vs bot B
As mentioned above, this server uses the true average for Pair(A,B); otherwise the calculations are the same.