◈ 학술지
◈ 도서
◈ 전자학술지
◈ 투고요령
◈ 수학신간도서
◈ MSC
◈ 논문검색
◈ 학술행사
홈 > 학술정보 >학술행사 > 세미나
2017 고려대학교 수학과 학술강연

Title
마르코프 의사결정과정과 강화학습
Speaker
황강욱   (KAIST )
Date
2017-11-10 16:30:00
Host
고려대학교
Place
아산이학관 526호
Abstract
Reinforcement learning is one of important areas in machine learning and artificial intelligence. It allows machines or software agents to automatically determine what are the best behaviors for a given environment. Reinforcement learning is based on Markov Decision Process(MDP). In this talk we examine what is MDP and investigate how to determine the best behaviors by using MDP. We also examine some related issues in the area of reinforcement learning.
개인정보보호정책 l 이메일주소집단수집금지 l 뷰어다운로드
qr코드