Timeline for How can I sample the output distribution multiple times when pruning the filters with reinforcement learning?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 27, 2020 at 15:00 | vote | accept | Habib-Allah | ||
| Apr 27, 2020 at 15:00 | |||||
| Apr 27, 2020 at 14:23 | comment | added | Brale | They write $\mathbf A_i \sim \pi(W, \theta)$ in Algorithm 1, this $\sim$ means they sample like I described. | |
| Apr 27, 2020 at 13:51 | comment | added | Habib-Allah | So this Ai=π(θ,W) means sampling the output distribution randomly ? I thought Ai=π(θ,W) means do something like Ai=agent.predict(W). Thanks :) | |
| Apr 27, 2020 at 13:42 | comment | added | Brale | Yes, that's exactly what I said in the previous comment. | |
| Apr 27, 2020 at 13:26 | comment | added | Habib-Allah | In the paper (Algorithm 1) they say sample the output distribution & then write Ai=π(θ,W). I'm confused i think. anyway thank you I will try what you said. | |
| Apr 27, 2020 at 13:11 | comment | added | Brale |
That's not what sampling means, sampling translated to code (Python) is something like this : random.random() < prob. It's like flipping a coin. If random number is lower than probability that means you set array element to 0 (or 1 depending what you want to do).
|
|
| Apr 27, 2020 at 12:55 | comment | added | Habib-Allah | Thanks for your answer! but how can I get these two arrays [0,1,1],[0,0,1] ?in order to sample I normally would do something like action=model.predict(W), if I sample another time I will get the same action array, won't I ? please tell me what I'm missing. | |
| Apr 27, 2020 at 11:18 | history | edited | Brale | CC BY-SA 4.0 |
corrected the answer; deleted 11 characters in body
|
| Apr 27, 2020 at 11:09 | history | answered | Brale | CC BY-SA 4.0 |