Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 99

0% of course complete

99Sarsa: On-Policy TD Control for Reinforcement Learning

Module 1 · Sarsa Control Algorithm

ARTICLEWhen and Why Sarsa Converges

Reinforcement LearningSarsa: On-Policy TD Control for Reinforcement Learning

ARTICLE

When and Why Sarsa Converges

Loading lesson…

← PREVIOUSHow Sarsa Learns While It Acts

NEXT →Understanding the Windy Gridworld Task

LESSON PROGRESS

In progress

0%

NEXT LESSON

Understanding the Windy Gridworld Task›