TD Learning: Temporal Difference Learning

In course

Ut irure esse nisi eiusmod pariatur non aute exercitation ex nisi eu cillum consequat magna. Qui et proident voluptate esse Lorem do deserunt. Et id magna qui magna cillum officia eu adipisicing est in aliqua. Labore cupidatat esse dolore ullamco amet cillum aliqua cupidatat occaecat. Anim anim sit dolore cillum excepteur ullamco in veniam dolore do labore. Nisi officia nisi aliqua irure occaecat consequat aliquip proident officia deserunt.

Description

This lecture introduces Temporal Difference Learning (TD learning) and the standard TD(0) algorithm for estimating values in reinforcement learning. It covers the concept of V-values, state-values, and the Bellman equation for value consistency of neighboring states. The lecture also explains how TD methods explore the graph over time, compare values at neighboring time steps, and update values based on 'temporal difference'.

Instructor

nulla cillum

Reprehenderit ex veniam minim sint eu minim labore in deserunt nulla. Esse amet nulla sunt enim aliqua incididunt ad voluptate adipisicing et ipsum ex magna. Ex reprehenderit consequat cillum ea et Lorem. Cupidatat enim exercitation do aliqua elit minim ex eu occaecat fugiat aliquip. Minim aliqua sunt fugiat commodo nostrud. Ullamco ullamco duis ad consequat cillum adipisicing duis cupidatat fugiat id adipisicing velit.

Official source

https://mediaspace.epfl.ch/media/0_eehycr7q

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)