Timeline for Proof that any $\epsilon$-greedy policy is an improvement over any $\epsilon$-soft policy
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 20, 2020 at 2:37 | comment | added | FantasticAI | why $ q_{\pi}(s,\pi^{'}(s)) = \sum_{a}\pi^{'}(a|s)q(s,a)$ holds? It really confuses me | |
| S Jul 21, 2019 at 12:49 | history | suggested | robertspierre | CC BY-SA 4.0 |
minor latex stylistic
|
| Jul 21, 2019 at 9:36 | comment | added | robertspierre | Thank you, I understand it now | |
| Jul 21, 2019 at 9:36 | vote | accept | robertspierre | ||
| Jul 21, 2019 at 9:36 | review | Suggested edits | |||
| S Jul 21, 2019 at 12:49 | |||||
| Jul 21, 2019 at 2:15 | review | First posts | |||
| Jul 21, 2019 at 6:36 | |||||
| Jul 21, 2019 at 2:12 | history | answered | M.Q | CC BY-SA 4.0 |