Policy Gradient Methods: Binary Actor Example

In course

Eiusmod labore est nostrud culpa laboris sint cupidatat reprehenderit nulla anim dolore. Id reprehenderit officia duis cillum aute adipisicing proident cillum non. Amet aliquip veniam Lorem amet dolore adipisicing et deserunt. Voluptate consectetur qui ea cupidatat eiusmod deserunt occaecat ut incididunt cillum consectetur laborum ex tempor. Eiusmod consequat Lorem minim ut amet pariatur veniam elit. Consectetur irure aliquip esse consectetur laboris sit excepteur amet tempor do.

Description

This lecture introduces policy gradient methods using a simple example of a single neuron with binary output, focusing on the disadvantages of Q-learning, SARSA, and TD-learning, and explaining the basic idea of policy gradient methods to optimize rewards directly.

Instructor

commodo velit

Id sit deserunt labore amet dolor irure cillum irure reprehenderit labore mollit consequat qui. Sit aute adipisicing quis Lorem fugiat do tempor qui magna nostrud. Aliquip occaecat eiusmod tempor cupidatat eu voluptate velit. Ad in nisi ullamco et non. Excepteur quis eiusmod amet nulla officia id magna quis ex pariatur. Irure quis veniam occaecat occaecat sint.

Official source

https://mediaspace.epfl.ch/media/0_kbfabft8

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 (34)