Table of ContentsChapter 5: Monte Carlo Methods Monte Carlo Policy Evaluation First-visit Monte Carlo policy evaluation Blackjack example Blackjack value functions Backup diagram for Monte Carlo The Power of Monte Carlo Two Approaches Monte Carlo Estimation of Action Values (Q) Monte Carlo Control Convergence of MC Control Monte Carlo Exploring Starts Blackjack example continued On-policy Monte Carlo Control On-policy MC Control Off-policy Monte Carlo control Learning about p while following Off-policy MC control Incremental Implementation Racetrack Exercise Summary |
Author: Andy Barto
Email: barto@cs.umass.edu |