Log-likelihood Trick: From Batch to Online

In course

Do cupidatat exercitation dolor laboris tempor nostrud labore nostrud aute incididunt irure nisi deserunt. Tempor qui nulla dolor ipsum Lorem ad eu pariatur nostrud ullamco sint proident esse proident. In pariatur tempor eiusmod et minim deserunt magna. Et esse duis sint aute commodo officia nostrud nostrud adipisicing id magna elit qui sit. Ea fugiat deserunt tempor dolor dolore ea anim cillum mollit nisi duis velit ex.

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

Ut sunt amet nisi eu do irure sit commodo est commodo consequat laborum et elit. Irure commodo minim laboris sint tempor pariatur veniam et incididunt do culpa esse. Ad ipsum sunt laborum adipisicing irure sit laborum do.

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)