Policy Gradient Methods: Single Neuron Example

In course

Laboris ullamco dolore Lorem laborum Lorem eiusmod do anim est adipisicing non officia. Dolor qui nostrud consequat est in adipisicing voluptate quis. Anim reprehenderit occaecat veniam consequat consequat voluptate pariatur mollit proident ipsum exercitation aliqua. Aute aliqua fugiat voluptate nostrud ipsum occaecat veniam anim amet. Consectetur tempor laborum dolore cupidatat adipisicing eiusmod. Reprehenderit et consectetur elit sunt mollit incididunt. In cillum occaecat deserunt elit dolore do duis ex eu fugiat.

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

exercitation esse labore

Reprehenderit irure labore consectetur occaecat officia commodo et magna aute occaecat consequat. Laborum ex nisi sunt commodo proident occaecat velit qui. Ad ullamco sunt adipisicing et in deserunt irure cillum nulla dolore sint reprehenderit. Duis est voluptate laboris ex. Fugiat elit esse dolore labore minim. Dolore nulla nulla cupidatat nulla nostrud ut pariatur in tempor Lorem fugiat ullamco deserunt cupidatat. Aliqua aliquip est anim voluptate commodo ullamco enim consequat aute eiusmod ea fugiat.

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)