Главная
Study mode:
on
1
Intro
2
Monte Carlo Methods
3
Actual vs. Simulated Experienc
4
MC Methods use Sampling
5
Monte Carlo Prediction
6
Syntax Note
7
MC Example: Blackjack
8
Ex: Blackjack Hand (Episode)
9
Blackjack Using DP?
10
Generalized Policy Iteration
11
MC Policy Iteration
12
Blackjack Policy
13
Monte Carlo ES
14
Monte Carlo Overview
15
Matchbox Machine Learning
16
Exam Questions
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore Monte Carlo Reinforcement Learning methods in this comprehensive lecture from the Intro to Artificial Intelligence course at Memorial University. Delve into the fundamentals of Monte Carlo techniques, comparing actual vs. simulated experiences, and understand how MC methods utilize sampling. Examine Monte Carlo prediction and its application in games like Blackjack. Learn about generalized policy iteration, Monte Carlo policy iteration, and the Monte Carlo ES algorithm. Gain insights into the Matchbox Machine Learning concept and prepare for potential exam questions on the topic. This 49-minute lecture, delivered by Professor David Churchill, offers a thorough introduction to Monte Carlo RL methods as part of the broader AI curriculum.

Introduction to Artificial Intelligence: Monte Carlo Reinforcement Learning Methods - Lecture 16

Dave Churchill
Add to list
0:00 / 0:00