Template:MDP와 Q 러닝: Revision history

From IT Wiki

Diff selection: Mark the radio buttons of the revisions to compare and hit enter or the button at the bottom.
Legend: (cur) = difference with latest revision, (prev) = difference with preceding revision, m = minor edit.

    28 October 2019

    • curprev 22:0422:04, 28 October 2019‎ Aimaster talk contribs‎ 348 bytes +348‎ 새 문서: {| class="wikitable" |- ! 항목 !! MDP !! Q 러닝 |- | 결정 과정 || 전이확률T(s’,a,s) 계산 || 미래값(Q) 계산 |- | 정책(Policy) || π(s) = 𝑎𝑟𝑔𝑚...
Retrieved from "https://itwiki.kr/w/Template:MDP와_Q_러닝"