Timeline for Mean or Mode of Action Distribution when Evaluating Policy Gradient Agents
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 19, 2023 at 18:45 | vote | accept | Luca Anzalone | ||
| Apr 24, 2023 at 17:12 | comment | added | David | I think my last comment is still valid. Finding the mode could be non-trivial (though I suppose in a Beta it is will known). So, in this case, the advice would simply to be to use whichever gives the best performance. | |
| Apr 24, 2023 at 8:38 | history | edited | Luca Anzalone | CC BY-SA 4.0 |
deleted 5 characters in body
|
| Apr 24, 2023 at 8:37 | comment | added | Luca Anzalone | Sure, the Bernoulli is a bad example (I'll edit that) so assume you have a Beta instead (indeed, the action space is continuous), what you would do in that case? still choosing the modal action? If so, can you motivate further | |
| Apr 23, 2023 at 22:30 | comment | added | David | How could you choose the mean action from a Bernoulli distn? The mean is $p$, whereas the mode is 0 or 1. for a discrete distn, you would usually want to choose the modal action. In a continuous distribution, the mode might be complex to calculate so I’d recommend using the mean. | |
| Apr 23, 2023 at 13:31 | history | edited | Luca Anzalone | CC BY-SA 4.0 |
added more details to the question
|
| Apr 23, 2023 at 10:20 | answer | added | nbro | timeline score: 3 | |
| Apr 21, 2023 at 18:09 | history | asked | Luca Anzalone | CC BY-SA 4.0 |