Timeline for What are the differences between 1-step SARSA and SARSA?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 30, 2020 at 20:11 | vote | accept | ycenycute | ||
| Apr 30, 2020 at 7:38 | comment | added | Swakshar Deb | Q learning and 1step off policy SARA are not exactly the same algorithm. But both are off policy and both follow the behavior policy. But in Q learning you need not consider the importance sampling ratio but in 1 step off policy SARSA you have to know both the behavior policy and target policy (since you have to find the sampling ratio). | |
| Apr 29, 2020 at 21:11 | comment | added | ycenycute | Then what is the difference between Q-learning and 1-step off policy SARSA? I understand the algorithms are different. 1-step off policy SARSA uses importance sampling, and Q learning seems just following behavior policy. What would be different results applying these two algorithms? Are they equivalent theoretically? | |
| Apr 27, 2020 at 15:13 | comment | added | Swakshar Deb | Yes, one-step on-policy SARSA is called SARSA | |
| Apr 27, 2020 at 14:32 | comment | added | ycenycute | Thanks for your reply. Does that mean on-policy 1-step SARSA is the same as SARSA? | |
| Apr 27, 2020 at 12:47 | history | edited | Swakshar Deb | CC BY-SA 4.0 |
edited body
|
| Apr 27, 2020 at 12:07 | history | edited | nbro | CC BY-SA 4.0 |
added 10 characters in body
|
| Apr 27, 2020 at 7:14 | history | answered | Swakshar Deb | CC BY-SA 4.0 |