Part 1: Key Concepts in RL — Spinning Up documentation
6
Public whispers
6
Contributors
2026-07-26 09:47:31
First whispered
Public whispers on this page
Text Highlight2026-07-26 16:11:31
Original Highlight Excerpt
"A policy is a rule used by an agent to decide what actions to take."
Whisper Note
So basically it's just the brain of the agent, got it.
Text Highlight2026-07-26 13:08:31
Original Highlight Excerpt
"There is no information about the world which is hidden from the state."
Whisper Note
That's the theory, but in practice we only get observations, right?
Text Highlight2026-07-26 12:59:31
Original Highlight Excerpt
"There is no information about the world which is hidden from the state."
Whisper Note
So if the state is complete, we never need to infer anything? Seems too ideal for real life.
Text Highlight2026-07-26 10:05:31
Original Highlight Excerpt
"RL is the study of agents and how they learn by trial and error."
Whisper Note
I wish my ex understood this concept, would've saved us both time.
Text Highlight2026-07-26 09:56:31
Original Highlight Excerpt
"RL is the study of agents and how they learn by trial and error."
Whisper Note
So it's like training a dog but with math instead of treats?
Text Highlight2026-07-26 09:47:31
Original Highlight Excerpt
"RL is the study of agents and how they learn by trial and error."
Whisper Note
Trial and error, that's basically how I learned to cook, ha.
Share this page's whispers
Short link
https://domwhisper.com/s/7788162c2ca7Embed snippet
<iframe src="https://domwhisper.com/embed/7788162c2ca7" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on spinningup.openai.com
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension