get_policy {polle}R Documentation

Get Policy

Description

get_policy extracts the policy from a policy object or a policy evaluation object The policy is a function which take a policy data object as input and returns the policy actions.

Usage

get_policy(object, threshold = NULL)

Arguments

object

Object of class policy_object or policy_eval.

threshold

Numeric vector. Thresholds for the first stage policy function.

Value

function of class policy.

Examples

library("polle")
### Two stages:
d <- sim_two_stage(5e2, seed = 1)
pd <- policy_data(d,
  action = c("A_1", "A_2"),
  baseline = c("BB"),
  covariates = list(
    L = c("L_1", "L_2"),
    C = c("C_1", "C_2")
  ),
  utility = c("U_1", "U_2", "U_3")
)
pd

### V-restricted (Doubly Robust) Q-learning

# specifying the learner:
pl <- policy_learn(
  type = "drql",
  control = control_drql(qv_models = q_glm(formula = ~C))
)

# fitting the policy (object):
po <- pl(
  policy_data = pd,
  q_models = q_glm(),
  g_models = g_glm()
)

# getting and applying the policy:
head(get_policy(po)(pd))

# the policy learner can also be evaluated directly:
pe <- policy_eval(
  policy_data = pd,
  policy_learn = pl,
  q_models = q_glm(),
  g_models = g_glm()
)

# getting and applying the policy again:
head(get_policy(pe)(pd))

[Package polle version 1.5 Index]