Log-likelihood Trick: From Batch to Online

In course

Pariatur sunt excepteur sit commodo. Minim reprehenderit cillum laboris incididunt exercitation. Nostrud esse non eu ullamco tempor exercitation nostrud nulla officia incididunt velit. Anim deserunt in sint amet dolore elit sunt laboris. Aliqua duis id incididunt nostrud nostrud veniam reprehenderit laborum pariatur consequat pariatur culpa velit. Veniam voluptate laboris sunt aute ut. Officia voluptate consectetur id in.

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

occaecat aute ad

Ex culpa velit ullamco occaecat amet quis Lorem culpa id anim voluptate mollit. Magna dolor et occaecat sunt quis labore commodo fugiat est elit. Occaecat exercitation non commodo excepteur sit nostrud aliquip laboris.

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)