David Silver
Advanced Topics 2015 (COMPM050/COMPGI13)
Reinforcement Learning
Contact: [email protected]
Video-lectures available here
Lecture 1: Introduction to Reinforcement Learning
….
번역
Model-free Prediction & Control
RL이란 1) 일단, 해보고 => 경험 2) 자신을 평가하고 ==> evaluation , prediction 3) 평가한대로 자신을 업데이트 => improve, control 4) 1~3 반복 ==> Iteration http://www.kocw.net/home/search/kemView.do?kemId=1367683 Model-free Prediction Monte Carlo Approximation 무작위로 일단 해본다. 그 Read more…
