September 2023
Beginner to intermediate
1044 pages
27h 52m
Korean
Content preview from 핸즈온 머신러닝(3판)
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.
817
18
장
강화 학습
18.5
행동 평가: 신용 할당 문제
각 스텝에서 가장 좋은 행동이 무엇인지 알고 있다면 평소처럼 추정된 확률과 타깃 확률 사이
의 크로스 엔트로피를 최소화하도록 신경망을 훈련할 수 있습니다. 이는 일반적인 지도 학습
과 같습니다. 하지만 강화 학습에서 에이전트가 얻을 수 있는 가이드는 보상뿐입니다. 보상은
일반적으로 드물고 지연되어 나타납니다. 예를 들어 에이전트가
100
스텝 동안 막대의 균형을
유지했다면 이
100
번의 행동 중 어떤 것이 좋고, 어떤 것이 나쁜지 알 수 있을까요? 우리가 아
는 것은 마지막 행동 뒤에 막대가 쓰러졌다는 것뿐입니다. 하지만 모든 책임이 이 마지막 행동
에 있는 것은 당연히 아닙니다. 이를
신용 할당 문제
credit
assignment
problem
라고 합니다. 즉, 에이전
트가 보상을 받았을 때 어떤 행동 덕분인지 (혹은 탓인지) 알기 어렵습니다. 주인의 말을 잘 따
르고 몇 시간이 지나서 보상을 받은 강아지를 생각해보세요. 이 강아지는 무엇 때문에 보상을
받았는지 이해할 수 있을까요?
이 문제를 해결하기 위해 흔히 사용하는 전략은 행동이 일어난 후 각 단계마다
할인 계수
discount
factor
γ
(감마 )를 적용한 보상을 모두 합하여 행동을 평가하는 것입니다. 할인된 보상의 합을 행
동의
대가 ...
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.