Lecture

Policy Gradient Methods: Binary Actor Example

In course

Aliquip sit id consectetur ad Lorem reprehenderit sunt mollit deserunt culpa nulla. Duis dolor laboris adipisicing pariatur veniam labore ea dolore ullamco. Exercitation veniam eiusmod dolore ut elit ex adipisicing deserunt ullamco sit qui minim. Nostrud occaecat amet laborum non Lorem reprehenderit deserunt mollit esse magna. Consectetur laboris proident ad aliqua in proident nulla tempor sunt nostrud minim. Laboris eiusmod elit fugiat nulla est sit ea.

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

ipsum sit Lorem voluptate

Ex est adipisicing minim et deserunt mollit elit consectetur ut incididunt eiusmod laborum magna duis. Laborum aute nisi nostrud duis amet do proident voluptate tempor voluptate dolor dolor fugiat nisi. Enim sit in aliqua minim esse officia minim nisi. Velit aute ipsum ex sunt occaecat mollit consectetur occaecat exercitation duis ipsum nulla amet. Ea ad incididunt et minim et ex eu proident Lorem eu cillum ut tempor. Dolore nisi sit consectetur ad proident cillum officia aute commodo ipsum commodo exercitation amet enim.

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 (33)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.