Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 124

0% of course complete

124TD-Gammon: A Reinforcement Learning Application to Backgammon

Module 1 · TD-Gammon's Architecture and Learning

ARTICLEHow TD-Gammon Turned a Backgammon Position into a Value Estimate

Reinforcement LearningTD-Gammon: A Reinforcement Learning Application to Backgammon

ARTICLE

How TD-Gammon Turned a Backgammon Position into a Value Estimate

Loading lesson…

← PREVIOUSBackgammon Basics Quiz

NEXT →How TD-Gammon Learned from Its Own Games

LESSON PROGRESS

In progress

0%

NEXT LESSON

How TD-Gammon Learned from Its Own Games›