Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 6

0% of course complete

6Optimistic Initial Values for Exploration

Module 1 · Performance Comparison and Limitations

ARTICLEWhy Optimistic Initial Values Do Not Solve Exploration Everywhere

Reinforcement LearningOptimistic Initial Values for Exploration

ARTICLE

Why Optimistic Initial Values Do Not Solve Exploration Everywhere

Loading lesson…

← PREVIOUSHow Optimistic Initial Values Change Bandit Performance

NEXT →Introduction to Upper-Confidence-Bound Action Selection

LESSON PROGRESS

In progress

0%

NEXT LESSON

Introduction to Upper-Confidence-Bound Action Selection›