We’ve partnered with the This Week in Machine Learning & AI podcast for a 7 part series on Industrial AI. Check out Episode 5 below and download our latest paper exploring the unique challenges and requirements of Industrial AI.
In part 5 of TWIML AI’s Industrial AI podcast series, Sam Charrington catches up with Professor Sergey Levine, a roboticist at UC Berkeley. Sergey’s work focuses on how robotic learning techniques can be used to allow machines to autonomously acquire complex behavioral skills.
Sam and Sergey discuss deep reinforcement learning at length, including mastery v. generalized training, multi-task learning, transfer learning and how researchers are working towards using past experiences to accelerate future learning in robotics.
“One of the things that distinguishes humans from these learned models is that humans are actually always doing multi-task learning. We’re always doing multiple things at once. We’re looking for things in our environment, we’re worrying about what we’re going to have for dinner... perhaps a lot of our efficiency is down to this fact: we’re never learning anything truly from scratch.” - Sergey Levine
Listen to the full conversation with Sergey below. To learn more about how you can leverage reinforcement learning and AI in your own industrial systems, visit bons.ai.