May 2020
Beginner to intermediate
952 pages
24h 11m
Korean
Content preview from 핸즈온 머신러닝(2판): 사이킷런, 케라스, 텐서플로 2를 활용한 머신러닝, 딥러닝 완벽 실무
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
748
2
부
신경망과 딥러닝
그럼
DQN
을 어떻게 훈련할 수 있을까요? 주어진 상태-행동 쌍 (
s
,
a
)에 대해
DQN
이 계산
한 근사
Q
-가치를 생각해보겠습니다. 벨먼 식 덕분에 이 근사
Q
-가치는 상태
s
에서 행동
a
를
실행했을 때 관측된 보상
r
과 그 이후에 최적으로 행동해서 얻은 할인된 가치를 더한 값에 가능
한 한 가깝게 되어야 합니다. 이 미래의 할인된 가치를 추정하기 위해서는 간단하게 다음 상태
s
′와 모든 가능한 행동
a
′에 대해
DQN
을 실행하면 됩니다. 그럼 모든 가능한 행동에 대한 미
래의 근사
Q
-가치를 얻을 수 있습니다. 그다음에 (최적으로 행동할 것이라고 가정하기 때문
에) 가장 높은 것을 고르고 할인을 적용하면 할인된 미래 보상의 추정을 얻을 수 있습니다. 보
상
r
과 미래의 할인된 가치 추정을 더하면 [식
18
-
7
]과 같이 상태-행동 쌍 (
s
,
a
)에 대한 타깃
Q
-가치
y
(
s
,
a
)를 얻게 됩니다.
식
18-7
타깃
Q
-가치
Qsar Qsa
a
target
,·max,
()
= +
′′
()
′
γ
θ
이 타깃
Q
-가치로 경사 하강법을 사용해 훈련 단계를 수행할 수 있습니다. 구체적으로 말하면
추정된
Q
-가치
Q
(
s
,
a
)와 타깃
Q
-가치 사이의 제곱 오차를 최소화합니다(또는 알고리즘이
큰 오차에 민감하지 않도록 후버 손실을 사용합니다 ). 이것이 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.