DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #2 [13/13]

Research Engineer Matteo Hessel covers general value functions, GVFs as auxiliary tasks, and explains how to deal with scaling issues in algorithms.
Slides: dpmd.ai/deeprl2
Full video lecture series: dpmd.ai/DeepMindxUCL21

[@you8sand]

Thanks for the great lecture series! That is some unfortunate echoing audio around 17m 😢

[@furkanedizkan7202]

Thank you for these great lectures

[@perryb3206]

A great final lecture to an enjoyable series. Thank you very much Matteo :)

[@unknown3.3.34]

Can I take this course bro?
Planning to start this. I would like to learn RL but I'm Afride that I might take up the wrong course.
Can you suggeste some good courses on RL.

[@Ishaheennabi]

thankue for this series

[@ArbaouiBillel]

Thank you 😊

[@MrLost1432]

50k on first lecture and 4k in the final one. Just an interesting observation

[@imranqureshi4299]

It would be interesting to see the view counts over time for all such lecture playlists on YT. In some ways TV shows have the opposite observation where the finale is watched more than intermediate episodes.

[@MrLost1432]

@@imranqureshi4299 Interesting :)

[@MrLost1432]

Maybe because people going in, with the objective to learn something, feel more obliged to start from the beginning?

[@imranqureshi4299]

@@MrLost1432 I would agree with that. Stories also keep interest a lot longer than educational material without context

[@unknown3.3.34]

Can I take this course bro?
Planning to start this. I would like to learn RL but I'm Afride that I might take up the wrong course.
Can you suggeste some good courses on RL.

[@rylaczero3740]

Could use better thumbnails