Timeline for Is the initialisation of $V(s)$ and $\pi(s)$ really arbitrary in policy iteration?
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 21, 2022 at 10:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Mar 22, 2022 at 9:09 | history | edited | nbro | CC BY-SA 4.0 |
edited tags; edited title
|
| Mar 22, 2022 at 9:04 | history | edited | nbro | CC BY-SA 4.0 |
edited tags; edited title
|
| Mar 21, 2022 at 13:05 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Feb 19, 2022 at 11:08 | history | edited | Gregwar | CC BY-SA 4.0 |
added 218 characters in body
|
| Feb 19, 2022 at 10:43 | history | edited | Gregwar | CC BY-SA 4.0 |
edited title
|
| Feb 17, 2022 at 20:52 | answer | added | Neil Slater | timeline score: 1 | |
| Feb 17, 2022 at 13:38 | comment | added | Gregwar | (I think the thing is that $\gamma = 1$ can only be used if all episodes terminate, else it has to be $< 1$. Else the episode returns is not well-defined.) | |
| S Feb 17, 2022 at 13:27 | review | First questions | |||
| Feb 17, 2022 at 16:16 | |||||
| S Feb 17, 2022 at 13:27 | history | asked | Gregwar | CC BY-SA 4.0 |