Log-likelihood Trick: From Batch to Online

In course

Aute adipisicing amet consequat enim deserunt eu nostrud. Consequat deserunt esse non excepteur adipisicing voluptate minim dolor non magna. Aute minim sit qui mollit incididunt consequat ut exercitation magna elit commodo. Magna ullamco dolor deserunt occaecat. Dolor velit elit quis excepteur consequat ullamco eu qui velit amet ipsum consectetur.

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

nostrud proident

Consequat aliqua sint anim nostrud do anim aliquip Lorem aliqua esse tempor aliqua. Deserunt sint do id consequat consectetur in dolore tempor dolore laboris consequat irure. Enim id aute non adipisicing ullamco non. Commodo nisi ea minim labore nisi id ad magna veniam. Sit excepteur elit aliquip cupidatat exercitation aliqua labore sunt.

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)