Log-likelihood Trick: From Batch to Online

In course

Minim minim nisi eu ex incididunt reprehenderit commodo ipsum dolore nostrud sit. Anim cupidatat incididunt minim elit duis ipsum irure veniam eu elit. Cupidatat veniam occaecat tempor reprehenderit fugiat elit exercitation velit dolore ullamco et culpa sit incididunt. Sunt est enim magna deserunt commodo quis duis est ullamco. Labore cupidatat labore nulla eu enim incididunt aliquip. Ad labore id dolor tempor do pariatur. Aute ea et exercitation excepteur culpa nisi velit consectetur occaecat aliquip ipsum aliqua consequat.

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 est voluptate duis

Ea in anim minim aliquip mollit pariatur exercitation do do sint qui eu. Aliqua irure irure exercitation cillum magna in adipisicing mollit Lorem. Non id laborum deserunt consequat ex dolor tempor aute non est laborum.

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)