메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
SANGUK HWANG (THE CATHOLIC UNIVERSITY OF KOREA) JEONGHO KIM (KYUNG HEE UNIVERSITY) DONGNAM KO (THE CATHOLIC UNIVERSITY OF KOREA) CHOHONG MIN (EWHA WOMANS UNIVERSITY) BYUNGJOON LEE (THE CATHOLIC UNIVERSITY OF KOREA)
저널정보
한국산업응용수학회 JOURNAL OF THE KOREAN SOCIETY FOR INDUSTRIAL AND APPLIED MATHEMATICS Journal of the Korean Society for Industrial and Applied Mathematics Vol.28 No.4
발행연도
2024.12
수록면
271 - 285 (15page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
The l-step lookahead strategy is a pivotal technique in value iteration methods, used extensively in sequential decision-making problems to anticipate future outcomes by considering a fixed number of steps l ahead. While this strategy achieves a high quality of decision at the cost of computational burden, its performance analysis inherently relies on the discount factor, which cannot fully capture its success in practical applications. In this work, we provide an explanation of the performance bound for l-step lookahead, based on two key components: the expectation of contraction and the relationship between value and strategy. Furthermore, we present two examples, Tetris and Flappy Bird, to observe the efficiency of value iteration more closely.

목차

ABSTRACT
1. INTRODUCTION
2. PRELIMINARIES
3. PRACTICAL PERFORMANCE OF THE l-STEP LOOKAHEAD POLICY
4. REFINED PERFORMANCE ESTIMATE ON THE l-STEP LOOKAHEAD POLICY
5. CONCLUSION
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-151-25-02-092128632