Part 1: Key Concepts in RL — Spinning Up documentation
6
公开标注数
6
参与人数
2026-07-26 09:47:31
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-26 16:11:31
原文高亮摘录
“A policy is a rule used by an agent to decide what actions to take.”
Whisper 随想笔记
So basically it's just the brain of the agent, got it.
划选高亮2026-07-26 13:08:31
原文高亮摘录
“There is no information about the world which is hidden from the state.”
Whisper 随想笔记
That's the theory, but in practice we only get observations, right?
划选高亮2026-07-26 12:59:31
原文高亮摘录
“There is no information about the world which is hidden from the state.”
Whisper 随想笔记
So if the state is complete, we never need to infer anything? Seems too ideal for real life.
划选高亮2026-07-26 10:05:31
原文高亮摘录
“RL is the study of agents and how they learn by trial and error.”
Whisper 随想笔记
I wish my ex understood this concept, would've saved us both time.
划选高亮2026-07-26 09:56:31
原文高亮摘录
“RL is the study of agents and how they learn by trial and error.”
Whisper 随想笔记
So it's like training a dog but with math instead of treats?
划选高亮2026-07-26 09:47:31
原文高亮摘录
“RL is the study of agents and how they learn by trial and error.”
Whisper 随想笔记
Trial and error, that's basically how I learned to cook, ha.
分享本页 Whisper
短链接
https://domwhisper.com/s/7788162c2ca7嵌入代码
<iframe src="https://domwhisper.com/embed/7788162c2ca7" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>