Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 85

0% of course complete

85Unifying n-step Action-Value Backups with Q(σ)

Module 1 · Off-policy n-step Q(σ) Algorithm

ARTICLEEstimating Q-values with Off-policy n-step Q(σ)

Reinforcement LearningUnifying n-step Action-Value Backups with Q(σ)

ARTICLE

Estimating Q-values with Off-policy n-step Q(σ)

Loading lesson…

← PREVIOUSn-step Q(σ) Basics Quiz

NEXT →How ε-greedy Policies Guide Off-policy n-step Q(σ)

LESSON PROGRESS

In progress

0%

NEXT LESSON

How ε-greedy Policies Guide Off-policy n-step Q(σ)›