Timeline for Large Deviation Principle for an adaptive sampling rule for Multi Armed Bandits
Current License: CC BY-SA 4.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 9 at 2:20 | history | edited | 29910622 | CC BY-SA 4.0 |
deleted 509 characters in body
|
| Oct 9 at 2:07 | history | edited | 29910622 | CC BY-SA 4.0 |
added 1 character in body
|
| Oct 9 at 2:06 | history | edited | 29910622 | CC BY-SA 4.0 |
added 505 characters in body
|
| Oct 9 at 1:58 | history | edited | 29910622 | CC BY-SA 4.0 |
added 1057 characters in body
|
| Oct 9 at 1:41 | comment | added | 29910622 | I guess on further thought it seems clear that the LDP rate function derived is always upper bounded by the heuristic guess. Hence the heuristic rate function is not the right rate function and the answer to question 2 is false. | |
| Oct 9 at 1:04 | history | edited | 29910622 | CC BY-SA 4.0 |
edited body
|
| Oct 9 at 1:04 | history | edited | 29910622 | CC BY-SA 4.0 |
added 1983 characters in body
|
| Oct 9 at 0:21 | history | edited | 29910622 | CC BY-SA 4.0 |
added 12 characters in body
|
| Oct 9 at 0:20 | history | edited | 29910622 | CC BY-SA 4.0 |
added 8 characters in body
|
| S Oct 9 at 0:18 | review | First questions | |||
| Oct 9 at 2:35 | |||||
| S Oct 9 at 0:18 | history | asked | 29910622 | CC BY-SA 4.0 |