Timeline for Why does Monte Carlo policy evaluation relies on action-value function rather than state-value function?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 20, 2020 at 14:09 | history | edited | calveeen | CC BY-SA 4.0 |
added 155 characters in body
|
| Nov 20, 2020 at 7:25 | comment | added | calveeen | Because SARSA update on the RHS utilises $Q(s',a')$. Also, as $a'$ is selected from the policy $\pi$, this is equivalent to the definition of $V^{\pi}$ | |
| Nov 20, 2020 at 5:43 | comment | added | Aung Khant | Awesome! Why are the formulas for V and Q the same in your answer? Isn't V = Pi * Q ? | |
| Nov 20, 2020 at 5:17 | vote | accept | Aung Khant | ||
| Nov 20, 2020 at 1:55 | history | answered | calveeen | CC BY-SA 4.0 |