Timeline for What is the difference between off-policy and on-policy learning?
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 1, 2017 at 16:50 | comment | added | Neil Slater | Off-policy methods are not only slower, but can be unstable when combined with bootstrapping (i.e. how Q-learning builds estimates from each other) and function approximators (e.g. neural networks). | |
| Aug 27, 2017 at 4:56 | review | Late answers | |||
| Aug 27, 2017 at 5:02 | |||||
| Aug 27, 2017 at 4:41 | history | answered | Juli | CC BY-SA 3.0 |