Timeline for What is the purpose of storing the action $a$ within an experience tuple?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 23, 2021 at 14:51 | vote | accept | bertushunzius | ||
| Feb 23, 2021 at 14:51 | comment | added | bertushunzius | I see. I think that answers my question, then :-) Thank you very much | |
| Feb 23, 2021 at 14:36 | comment | added | David | You're correct that we only update the Q-value for one action. I posted an answered here that seems like it might explain this in more detail. | |
| Feb 23, 2021 at 12:14 | comment | added | bertushunzius | Perhaps I now understand where my mistake was. Do I understand correctly, that for calculating the loss and performing gradient descent, we do not actually compare all of the Q-values, but only the one that corresponds to $Q(s,a)$ to its target value? Until now, I was under the impression we would do something like mean-squared-error, where we compare all the Q-values to their "labels" or rather the targets we calculated using $s'$ and $r$. | |
| Feb 22, 2021 at 14:58 | history | answered | David | CC BY-SA 4.0 |