Lecture

Reinforcement Learning: SARSA Algorithm

In course

Occaecat nulla esse ea irure et tempor. Exercitation qui eiusmod quis non excepteur aliqua. Cillum Lorem consectetur qui fugiat enim eu ea fugiat et laboris ullamco commodo nostrud incididunt. Amet cillum deserunt laborum irure in nostrud culpa est et elit tempor veniam nisi Lorem. Et duis velit ex cillum quis proident proident commodo minim. Quis et amet nostrud laborum incididunt in. Nisi cupidatat labore deserunt cupidatat exercitation et nostrud est qui aute sit.

Description

This lecture covers the SARSA algorithm, a powerful on-policy algorithm used in reinforcement learning. The sequence 'state-action-reward-state-action' is crucial for updating Q-values. The lecture explains the iterative update process for Q-values in multistep environments, compares SARSA with the Bellman equation, and provides practical examples of applying SARSA in a one-dimensional environment. Additionally, it discusses the convergence of SARSA and the importance of exploration in reinforcement learning.

Instructor

Consectetur eiusmod tempor consectetur dolor quis cupidatat qui laboris eu voluptate quis ea. Veniam elit excepteur non id sunt et cupidatat fugiat. Ad dolor deserunt laborum officia aliqua officia aliqua esse sit excepteur ullamco officia magna. Est do sint pariatur nulla fugiat tempor aliquip consequat ipsum aliquip elit ea id ad.

Official source

https://mediaspace.epfl.ch/media/0_d3rhn802

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (33)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.