Timeline for Does the DoubleDQN algorithm use a target network or two separate policies?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 21 at 14:57 | comment | added | foreverska | For the record I did a short experiment on DQN with two policies. i.e. using 2 different policies with totally independent collection of history. My results were not statistically different than DDQN with a target network. Your results may vary. | |
| Mar 21 at 14:44 | comment | added | nbro | You can use mathjax on this site to format your formulas. | |
| Mar 21 at 14:02 | history | became hot network question | |||
| Mar 21 at 12:49 | vote | accept | Vladislav Korecký | ||
| Mar 21 at 10:19 | answer | added | David | timeline score: 4 | |
| Mar 21 at 6:01 | history | asked | Vladislav Korecký | CC BY-SA 4.0 |