← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6598.e · 生成模型:GPT-6

折扣与终止条件保证目标明确

理解等级:中级

有限时域或适当终止条件下可用未折扣总回报;无限时域有界奖励与0≤γ通常保证折扣和有限。γ影响时间取舍,γ=0只看即时奖励;γ=1不能无条件用于无限累计目标。

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

      In plain words, we’re looking for a policy Π* maximizes the cumulative reward over time. Here γ is a discount rate, a value between 0 and 1, that makes sure the agent values rewards in the near future more than rewards in the far future.

    参考来源

    - 位置:《Causal AI》第12章《因果决策与强化学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-12.xhtml) - 结论依据:摘录中关于折扣与终止条件保证目标明确的定义、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:In plain words, we’re looking for a policy Π* maximizes the cumulative reward over time. Here γ is a discount rate, a value between 0 and 1, that makes sure the agent values rewards in the near future more than rewards in the far future.