Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 25

0% of course complete

25Expected Sarsa: Improving TD Control

Module 0 · Understanding Expected Sarsa

ARTICLEExpected Sarsa: Improving TD Control

Reinforcement LearningExpected Sarsa: Improving TD Control

ARTICLE

Expected Sarsa: Improving TD Control

Loading lesson…

← PREVIOUSWhy Batch TD(0) Converges to the Certainty-Equivalence Estimate

NEXT →Expected Sarsa Compared with Sarsa and Q-learning

LESSON PROGRESS

In progress

0%

NEXT LESSON

Expected Sarsa Compared with Sarsa and Q-learning›