Qlearning_gglasso: Qlearning_gglasso This is the main function of Q-learning or...

Description Usage Arguments Value Examples

Description

Qlearning_gglasso This is the main function of Q-learning or penalized Q-learning

Usage

1
Qlearning_gglasso(H, A, R, pA, pentype = "lasso", group, loss = "ls", m = 10)

Arguments

H:

n by p matrix of features

A:

treatment vector of length n, A_i = +1 or -1

R:

outcome vector of length n

pA:

propensity score, vector of length n

pentype:

whether penalized Q-learning is used or not, default is "lasso"

group:

group number, vector of length (2p+1), have to be consective, in each individual is one group then set group=seq(1: (2p+1))

loss:

default is "ls" for least square loss

Value

subject of class "qlearn"

Examples

1
Qlearning_gglasso(H,A,R, pA)

sambiostat/WAPL documentation built on May 26, 2020, 12:17 a.m.