Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 96

0% of course complete

96Off-policy Prediction with Importance Sampling

Module 2 · Examples and Challenges in Off-policy Learning

ARTICLEEstimating a Blackjack State Value Off-Policy

Reinforcement LearningOff-policy Prediction with Importance Sampling

ARTICLE

Estimating a Blackjack State Value Off-Policy

Loading lesson…

← PREVIOUSImportance Sampling Quiz

NEXT →Why Off-policy Estimates Can Have Infinite Variance

LESSON PROGRESS

In progress

0%

NEXT LESSON

Why Off-policy Estimates Can Have Infinite Variance›