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

November 27, 2019 • 01:15:24

BI 054 Kanaka Rajan: How Do We Switch Behaviors?

Kanaka and I discuss a few different ways she uses recurrent neural networks to understand how brains give rise to behaviors. We talk about...

Episode 0

April 15, 2022 • 01:29:14

BI 133 Ken Paller: Lucid Dreaming, Memory, and Sleep

Support the show to get full episodes and join the Discord community. Check out my short video series about what's missing in AI and...

Episode 0

May 27, 2023 • 01:27:43

BI 167 Panayiota Poirazi: AI Brains Need Dendrites

Support the show to get full episodes and join the Discord community. Check out my free video series about what's missing in AI and...