Timeline for Replay buffer action range in DDPG
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 27, 2022 at 13:26 | comment | added | Rémy Hosseinkhan Boucher | @DavidIreland ok sorry:) | |
| Jul 26, 2022 at 21:00 | comment | added | David | @RémyHosseinkhanBoucher yes, I am fully aware. Here, OP doesn’t have a symmetric action space so it would make more sense to use sigmoid as this outputs in $(0, 1)$ and you can multiply the output by $x$ to get an action in the range $(0, x)$ | |
| Jul 26, 2022 at 20:45 | comment | added | Rémy Hosseinkhan Boucher | @DavidIreland tanh is used in order to have an action distribution (policy) possibly centered around zero. | |
| Jun 16, 2022 at 8:50 | answer | added | goldfinch | timeline score: 1 | |
| May 25, 2022 at 13:27 | comment | added | David | I think it would make more sense to have your network use a sigmoid activation and then multiply the action by 1.57 as part of the network, and then everything should work out. | |
| May 24, 2022 at 20:03 | history | edited | goldfinch |
edited tags
|
|
| S May 24, 2022 at 20:00 | review | First questions | |||
| May 24, 2022 at 21:36 | |||||
| S May 24, 2022 at 20:00 | history | asked | goldfinch | CC BY-SA 4.0 |