UIpac (Show me the what to do!)

Multi-armed Bandit Problem 본문

Information/AI | Data | Device

Multi-armed Bandit Problem

David.Cheon 2017.10.29 20:17
강화학습 알고리즘의  줄기를 차지하고 있는 Multi-armed bandit problem 대한 내용입니다. 
동영상에서는 Multi-armed bandit problem 어떤 목적을 지니는지,  알고리즘은 어떻게 생긴건지에 대한 개념을 정리한 영상입니다. 

영상 목차 

- Multi-armed bandit problem (MABP)이란 무엇인가?

- Stochastic, Non-stochastic, Markovian MABP 모델 설명

- MABP 알고리즘인 Exp3




0 Comments
댓글쓰기 폼