Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 46

0% of course complete

46Understanding Instability in Semi-Gradient Methods

Module 1 · Stability Issues with Other Methods

ARTICLEWhy Q-Learning and Least-Squares DP Can Become Unstable

Reinforcement LearningUnderstanding Instability in Semi-Gradient Methods

ARTICLE

Why Q-Learning and Least-Squares DP Can Become Unstable

Loading lesson…

← PREVIOUSBaird's Counterexample Quiz

NEXT →Averagers as a Solution to Instability

LESSON PROGRESS

In progress

0%

NEXT LESSON

Averagers as a Solution to Instability›