Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 4

0% of course complete

4Efficient Action-Value Estimation

Module 0 · Incremental Computation

ARTICLEWhy Action-Value Averages Need Incremental Computation

Reinforcement LearningEfficient Action-Value Estimation

ARTICLE

Why Action-Value Averages Need Incremental Computation

Loading lesson…

← PREVIOUSGreedy Action Selection

NEXT →Incremental Update Rule

LESSON PROGRESS

In progress

0%

NEXT LESSON

Incremental Update Rule›