Add references to Lihong Li et all (2010)

Closes #11

Author: robinvanemden

R/policy_cmab_lin_ucb_disjoint.R

@@ -51,6 +51,10 @@ LinUCBDisjointPolicy <- R6::R6Class(
 
 #' Policy: LinUCB with unique linear models
 #'
+#' LinUCBDisjointPolicy is an R implementation of
+#' "Algorithm 1 LinUCB" from Li (2010) "A contextual-bandit approach to
+#' personalized news article recommendation.".
+#'
 #' Each time step t, \code{LinUCBDisjointPolicy} runs a linear regression per arm that produces coefficients
 #' for each context feature \code{d}.
 #' Next,  \code{LinUCBDisjointPolicy} observes the new context, and generates a predicted payoff or reward

R/policy_cmab_lin_ucb_disjoint_optimized.R

@@ -50,6 +50,10 @@ LinUCBDisjointOptimizedPolicy <- R6::R6Class(
 
 #' Policy: LinUCB with unique linear models
 #'
+#' LinUCBDisjointOptimizedPolicy is an optimized R implementation of
+#' "Algorithm 1 LinUCB" from Li (2010) "A contextual-bandit approach to
+#' personalized news article recommendation.".
+#'
 #' Each time step t, \code{LinUCBDisjointPolicy} runs a linear regression per arm that produces coefficients
 #' for each context feature \code{d}.
 #' Next,  \code{LinUCBDisjointPolicy} observes the new context, and generates a predicted payoff or reward

R/policy_cmab_lin_ucb_hybrid.R

@@ -115,6 +115,10 @@ LinUCBHybridPolicy <- R6::R6Class(
 
 #' Policy: LinUCB with hybrid linear models
 #'
+#' LinUCBHybridPolicy is an R implementation of
+#' "Algorithm 2 LinUCB" from Li (2010) "A contextual-bandit approach to
+#' personalized news article recommendation.".
+#'
 #' Each time step t, \code{LinUCBHybridOptimizedPolicy} runs a linear regression per arm that produces
 #' coefficients for each context feature \code{d}. Next, it observes the new context, and generates a
 #' predicted payoff or reward together with a confidence interval for each available arm. It then proceeds

R/policy_cmab_lin_ucb_hybrid_optimized.R

@@ -119,6 +119,10 @@ LinUCBHybridOptimizedPolicy <- R6::R6Class(
 
 #' Policy: LinUCB with hybrid linear models
 #'
+#' LinUCBHybridOptimizedPolicy is an optimized R implementation of
+#' "Algorithm 2 LinUCB" from Li (2010) "A contextual-bandit approach to
+#' personalized news article recommendation.".
+#'
 #' Each time step t, \code{LinUCBHybridOptimizedPolicy} runs a linear regression per arm that produces
 #' coefficients for each context feature \code{d}. Next, it observes the new context, and generates a
 #' predicted payoff or reward together with a confidence interval for each available arm. It then proceeds