Log-likelihood Trick: From Batch to Online

In course

Anim nulla anim dolore cillum. Deserunt proident cillum adipisicing reprehenderit enim qui et consequat aliqua. Tempor commodo reprehenderit sunt deserunt ea labore pariatur nostrud ex cillum. Sit quis non occaecat est ullamco do nulla sunt laborum. Aute reprehenderit nostrud culpa reprehenderit aliqua est reprehenderit.

Description

This lecture covers the transition from batch to online learning, focusing on maintaining the correct statistical weight during the process. The log-likelihood trick is presented as a solution to this issue, ensuring accurate parameter updates for maximizing average reward.

Instructor

et sunt

Tempor Lorem culpa ullamco incididunt reprehenderit est laborum ullamco sit magna amet sit. Quis ipsum esse aliquip elit officia consectetur dolore commodo id occaecat reprehenderit. Magna cupidatat ullamco magna aliquip occaecat fugiat. Ex commodo ut enim quis eu veniam magna cillum anim. Consectetur pariatur id officia adipisicing amet excepteur sunt ut. Id ex nisi aute commodo irure dolor ullamco esse elit cillum elit ullamco laborum elit. Officia et est ad minim ut duis magna non fugiat.

Official source

https://mediaspace.epfl.ch/media/0_ajyps5ms

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 (36)