← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6561.e · 生成模型:GPT-6

已知输法会改变反事实问题

理解等级:中级

标准三门规则下,已知保持首选而输,首选必为无奖门,因此若当时换门会赢。只知道输了却不知道策略时,输者中还包括换门后输的人;用书中均匀独立初选及各半策略,可得改成换门后赢的条件概率2/3。两问题不能混为同一个2/3。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      For a player who stayed with their first door and lost, what is the probability that they would have won if they switched doors? For a player who lost, what is the probability that they would have won if they switched doors? We’ll answer these questions with the following steps: Build the parallel world model as a generative graphical model in pgmpy. Condition on evidence

    参考来源

    - 位置:《Causal AI》第09章《通用反事实推断算法》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-9.xhtml) - 结论依据:摘录中关于已知输法会改变反事实问题的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:For a player who stayed with their first door and lost, what is the probability that they would have won if they switched doors? For a player who lost, what is the probability that they would have won if they switched doors? We’ll answer these questions with the following steps: Build the parallel world model as a generative graphical model in pgmpy. Condition on evidence