Courses
Concepts
Explore
Playground
Practice
Log in
Course contents
← Back to course
Reinforcement Learning
You are in chapter 85
0% of course complete
85
Unifying n-step Action-Value Backups with Q(σ)
Module 0 · Introduction to n-step Q(σ)
→
ARTICLE
How n-step Q(σ) Unifies Action-Value Backups
›
Reinforcement Learning
›
Unifying n-step Action-Value Backups with Q(σ)
ARTICLE
How n-step Q(σ) Unifies Action-Value Backups
Loading lesson…
← PREVIOUS
How n Changes the Performance of TD Methods
MARK COMPLETE ✓
NEXT →
Controlling Sampling in n-step Q(σ)
