COMP 3200 / 6980 - Intro to Artificial Intelligence - Lecture 17 - Bandit Algorithms
Автор: Dave Churchill
Загружено: 2026-03-16
Просмотров: 94
Описание:
00:00 - Intro + Exploitation vs Exploration (EvE)
01:34 - Learning
03:04 - Exploitation
03:47 - Exploration
05:09 - N-Armed Bandit Problem
09:04 - Important EvE Concepts
12:04 - Action Value Methods
16:31 - Bandit Example
21:12 - Sample Average Estimation
26:12 - Incremental Average Formula
33:15 - Fixed-Size Alpha Incremental Update
41:00 - Action Selection Methods
41:14 - Greedy Action Selection
43:18 - Epsilon Greedy Selection
51:00 - Bandit Algorithm Pseudocode
55:55 - Upper Confidence Bound (UCB)
1:00:47 - Q(a) vs Q(s,a)
1:03:40 - Exam Questions
Memorial University - Computer Science 3200 / 6980 - Winter 2026
Intro to Artificial Intelligence
Professor: David Churchill - http://www.cs.mun.ca/~dchurchill/
This course is an introduction to Artificial Intelligence (AI), covering algorithmic techniques and data structures used in modern problem-solving environments. Each topic will have a related assignment where the learned techniques are applied to simple games. This is the graduate version of COMP 3200.
Course Assignments / Files will not be released publicly
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке:
