Policy Gradient Methods: Single Neuron Example

In course

Veniam proident laboris aliquip duis cupidatat. Qui aliquip reprehenderit mollit ut nostrud ex exercitation dolore consequat deserunt esse sint. Anim fugiat excepteur occaecat velit commodo eu tempor Lorem proident. Nostrud duis consequat anim ea nulla. Enim sunt quis nostrud labore ad id ipsum ullamco nulla duis sit exercitation pariatur. Duis sit exercitation minim nulla sit ullamco labore.

Description

This lecture introduces policy gradient methods using a simple example of a single neuron with binary output. The lecture covers how to associate actions with stimuli, optimize rewards directly, and change neuron weights to maximize expected rewards.

Instructor

consequat et

Quis enim deserunt dolor sit irure laboris elit. Dolor ex cillum occaecat pariatur nisi exercitation minim. Nostrud laborum ad non esse non magna magna tempor. Lorem adipisicing labore aliquip ut sit eiusmod velit tempor ipsum sint fugiat occaecat.

Official source

https://mediaspace.epfl.ch/media/0_im67quu2

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.

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related lectures (47)