반복영역 바로가기
주메뉴로 바로가기
좌측메뉴로 바로가기
본문으로 바로가기

Home News&ActivitySeminars

Seminars

프린트페이스북

(대학원생 마일리지 적용) 학과 세미나 안내 (4/1(월), 이상학 박사 at Purdue University / Seminar Notice: 4/1 at 2:00pm)

2019.03.29 10:13

교수님 및 학생분들께

 

안녕하세요학과조교 류희랑입니다.

학과 세미나가 다음과 같이 진행될 예정입니다.

 

1. 일시: 4 1(월) 오후 2

 

2. 장소: 산업경영학동(E2-2) 2층 교수회의실(2122)

 

3. 주제A Causal Perspective on Sequential Decision-Making Problems   

 

4. 연사: 이상학 박사, Postdoctoral scholar in the Department of Computer Science at Purdue University

 

5. 언어: 한국어 (Skype 화상 진행)

 

많은 관심과 참석 부탁드립니다.

 

감사합니다.

 

류희랑 올림.

 

----------------------------

 

Dear ISysE Professors and Students,

 

ISysE department invites you to attend the following seminar.

 

Speaker: Sanghack Lee, Postdoctoral scholar in the Department of Computer Science at Purdue University

Title: A Causal Perspective on Sequential Decision-Making Problems   

 

Date & Time: April 1st(Mon), 2:00 pm

Place: E2-2 Bldg, #2122

Language: Korean (proceed with Skype webcam)

 

We look forward to your attendance and encourage you to forward this invitation to colleagues who may be interested in the topic.

           

With best regards,

 

Heelang Ryu

 

----------------

 

 

Causal knowledge is sought after throughout data-driven fields due to its explanatory power and potential value to inform decision-making. If the targeted system is well-understood in terms of its causal components, one is able to design more precise and surgical interventions so as to bring certain desired outcomes about. In this talk I will first introduce general ideas on how Structural Causal Model provides a semantical framework to understand sequential decision-making problems. Then, I will focus on recent progress on a structural causal bandit, a sequential decision-making setting where the reward distributions of the arms exhibit a non-trivial dependence structure, which is governed by the underlying causal model of the domain. I will discuss a number of structural properties implied by the underlying causal model. I will conclude the talk by discussing future research directions.

List