An R implementation of the TrueSkill Algorithm (Herbrich, R., Minka, T. and Grapel, T. [1]), a Bayesian skill rating system with inference by approximate message passing on a factor graph. Used by Xbox to rank gamers and identify appropriate matches.
Player
(Package: trueskill) :
Player: class to hold the rank, skill and names of players
Reference class to create objects that represent players.
● Data Source:
CranContrib
● Keywords:
● Alias: Player
●
0 images
Parameters
(Package: trueskill) :
Sets three parameters used in the TrueSkill algorithm.
Class creates an object to hold three parameters used in the TrueSkill algorithm. Passed to AdjustPlayer and Trueskill to perform calculations and update the Player objects or data. The default parameters object is: "Parameters [(beta, epilson, gamma)]: [(4.167, 0.74, 0.083)]" where the default inputs are: INITIAL_MU = 25.0 INITIAL_SIGMA = INITIAL_MU / 3.0 INITIAL_BETA = INITIAL_SIGMA / 2.0 INITIAL_GAMMA = INITIAL_SIGMA / 100.0 DRAW_PROBABILITY = 0.10 INITIAL_EPSILON = DrawMargin(DRAW_PROBABILITY, BETA)
Reference Class to create objects that represent normal distributions, which is how players' skills are represented. Gaussian takes arguments (mu, sigma) or (pi, tau), which default to (0, Inf) or (0, 0), respectively. Note: for consistency reasons and not having to update two sets of values, the class only stores pi and tau. Therefore, g1$mu <- 25 and g1$sigma <- 8 does not work as expected, though g1$pi <- 0.04 and g1$tau <- 0.13 does.
Compute the draw probability given the draw margin (epsilon). Can be passed to DrawMargin to calculate EPSILON. Refer to Parameters for default input values.