BI 045 Raia Hadsell: Robotics and Deep RL

Brain Inspired

Aug 28 2019 | 01:16:52

00:00 / 01:16:52

Show Notes

Support the Podcast

Show notes:

Raia and I discuss her work at DeepMind figuring out how to build robots using deep reinforcement learning to do things like navigate cities and generalize intelligent behaviors across different tasks. We also talk about challenges specific for embodied AI (robots), how much of it takes inspiration from neuroscience, and lots more.

Raia’s website.
Follow her on Twitter: @RaiaHadsell
Papers relevant to our discussion:
A few Talks:
- Deep reinforcement learning in complex environments.
- Progressive Nets & Transfer.
The new Neuro-AI conference she’s starting with Tony Zador and Blake Richards:
- From Neuroscience to Artificially Intelligent Systems (NAISys)

Other Episodes

Episode 0

March 17, 2021 • 01:08:43

BI 100.3 Special: Can We Scale Up to AGI with Current Tech?

Part 3 in our 100th episode celebration. Previous guests answered the question: Given the continual surprising progress in AI powered by scaling up parameters...

Episode 0

March 13, 2022 • 01:00:56

BI 130 Eve Marder: Modulation of Networks

Support the show to get full episodes and join the Discord community. Eve discusses many of the lessons she has learned studying a small...

Episode 0

February 26, 2025 • 01:29:10

BI 206 Ciara Greene: Memories Are Useful, Not Accurate

Support the show to get full episodes, full archive, and join the Discord community. Ciara Greene is Associate Professor in the University College Dublin...