Timeline for Is there an algorithm that produces a uniform distribution over the set of trajectories with maximum reward sum?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 10 at 12:23 | history | edited | nbro | CC BY-SA 4.0 |
edited tags; edited title
|
| Apr 10 at 3:04 | history | became hot network question | |||
| Apr 9 at 21:48 | vote | accept | moe asal | ||
| Apr 9 at 21:40 | answer | added | Alberto | timeline score: 5 | |
| Apr 9 at 19:13 | answer | added | foreverska | timeline score: 2 | |
| Apr 9 at 19:01 | comment | added | moe asal | @foreverska yes, in a sense. All these optimal policies should be summarized by one model that, in a sense, samples uniformly from one of them. | |
| Apr 9 at 18:53 | comment | added | foreverska | Are you attempting to build a model which finds all (or many) optimal policies in an environment? | |
| S Apr 9 at 18:46 | review | First questions | |||
| Apr 9 at 21:45 | |||||
| S Apr 9 at 18:46 | history | asked | moe asal | CC BY-SA 4.0 |