Episode 43: Deep Reinforcement Learning

The Theory of Anything

English - April 18, 2022 07:00 - 1 hour - 74.8 MB
Philosophy Society & Culture Homepage Download Google Podcasts Overcast Castro Pocket Casts RSS feed

Previous Episode: Episode 42: Popper without Refutation & Resolving the Problems of Refutation (part 2)

Next Episode: Episode 44: Clarifying David Deutsch's Views of "Knowledge"

In this video upload available on Spotify (we'll try this once and see how it's received), we revisit Reinforcement Learning (from way back in episode 28) and this time discuss how to turn it into Deep Reinforcement Learning by swapping out the Q-Table and putting a neural network in its place. The end result is a sort of 'bootstrapping intelligence' where you let the neural net train itself.

We also discuss:

How this, if at all, relates to animal intelligence.
Is RL a general purposes learner?
Is it a path to AGI?

Links:

Github Code Base
Presentation Slide Pack
Youtube version

---

Support this podcast: https://podcasters.spotify.com/pod/show/four-strands/support