Package index
-
LinTSModel() - Linear Thompson Sampling model.
-
aw_estimate() - Estimate policy value via non-contextual adaptive weighting.
-
aw_scores() - Compute AIPW/doubly robust scores.
-
aw_var() - Variance of policy value estimator via non-contextual adaptive weighting.
-
calculate_balwts() - Calculate balancing weight scores.
-
calculate_continuous_X_statistics() - Estimate/variance of policy evaluation via contextual weighting.
-
draw_thompson() - Thompson Sampling draws.
-
estimate() - Estimate/variance of policy evaluation via non-contextual weighting.
-
generate_bandit_data() - Generate classification data.
-
ifelse_clip() - Clip lamb values between a minimum x and maximum y.
-
impose_floor() - Impose probability floor.
-
output_estimates() - Policy evaluation with adaptively generated data.
-
plot_cumulative_assignment() - Plot cumulative assignment for bandit experiment.
-
ridge_init() - Ridge Regression Initialization for Arm Expected Rewards
-
ridge_muhat_lfo_pai() - Leave-future-out ridge-based estimates for arm expected rewards.
-
ridge_update() - Updates ridge regression matrices.
-
run_experiment() - Run an experiment using Thompson Sampling.
-
simple_tree_data() - Generate simple tree data.
-
stick_breaking() - Stick breaking function.
-
twopoint_stable_var_ratio() - Calculate allocation ratio for a two-point stable-variance bandit.
-
update_thompson() - Update linear Thompson Sampling model.