问题描述
所以我使用这些线来绘制我的强盗政策,但所有这些都具有完全相同的累积奖励率。这不可能。我在这里做错了什么?提前致谢! :)
simulations <- 1
horizon <- nrow(atukunda_a) #My dataset is atukunda_a
log_S <- atukunda_a #This is the data
formula <- "blood_loss_24hrs ~ study_group" #reward ~ arms
bandit <- OfflineReplayEvaluatorBandit$new(formula,log_S)
#?RandomPolicy
agents <-
list(Agent$new(ThompsonSamplingPolicy$new(1.0,1.0),bandit,"ThompsonSampling"),Agent$new(UCB1Policy$new(),"UCB1"))
simulation <-
Simulator$new(
agents = agents,simulations = simulations,horizon = horizon,save_context = FALSE,progress_file = TRUE,do_parallel = FALSE
)
sim <- simulation$run()
plot(sim,type = "cumulative",legend_title = "Simulation",rate = TRUE,regret = FALSE,legend_position = "bottomright")
解决方法
暂无找到可以解决该程序问题的有效方法,小编努力寻找整理中!
如果你已经找到好的解决方法,欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@)