Today we’re taking a deep dive into the latest and greatest in the world of Reinforcement Learning with our friend Sergey Levine, an associate professor, at UC Berkeley. In our conversation with Sergey, we explore some game-changing developments in the field including the release of ChatGPT and the onset of RLHF. We also explore more broadly the intersection of RL and language models, as well as advancements in offline RL and pre-training for robotics models, inverse RL, Q learning, and a host of papers along the way. Finally, you don’t want to miss Sergey’s predictions for the top developments of the year 2023! The complete show notes for this episode can be found at twimlai.com/go/612

Sergey Levine, an assistant professor of EECS at UC Berkeley, is one of the pioneers of modern deep reinforcement learning. His research focuses on developing general-purpose algorithms for autonomous agents to learn how to solve any task. In this episode, we talk about the bottlenecks to generalization in reinforcement learning, why simulation is doomed to succeed, and how to pick good research problems.

Sergey Levine, an assistant professor at UC Berkeley, dives into the fascinating world of autonomous learning in robots. He discusses how robots can evolve from performing specific tasks to teaching themselves and each other. The conversation covers the complexities of reinforcement learning, comparing robot adaptability to human learning. Sergey also envisions a future where robots enhance human life, assist the disabled, and tackle hazardous jobs. With transformative potential on the horizon, he highlights both the challenges and the exciting possibilities in robotics.

Discover the latest advancements in AI-controlled robots with Sergey Levine, exploring reinforcement learning and embodied AI. Learn about the RTX project enhancing robots' ability to perform diverse tasks. Dive into the intersection of AI, robotics, and the quest for adaptable machines revolutionizing technology.

Sergey Levine is a professor at Berkeley and a world-class researcher in deep learning, reinforcement learning, robotics, and computer vision, including the development of algorithms for end-to-end training of neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, and deep RL algorithms. Support this podcast by supporting these sponsors: – ExpressVPN: https://www.expressvpn.com/lexpod – Cash App – use code “LexPodcast” and download: – Cash App (App Store): https://apple.co/2sPrUHe – Cash App (Google Play): https://bit.ly/2MlvP5w If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts, follow on Spotify, or support it on Patreon. Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time. OUTLINE: 00:00 – Introduction 03:05 – State-of-the-art robots vs humans 16:13 – Robotics may help us understand intelligence 22:49 – End-to-end learning in robotics 27:01 – Canonical problem in robotics 31:44 – Commonsense reasoning in robotics 34:41 – Can we solve robotics through learning? 44:55 – What is reinforcement learning? 1:06:36 – Tesla Autopilot 1:08:15 – Simulation in reinforcement learning 1:13:46 – Can we learn gravity from data? 1:16:03 – Self-play 1:17:39 – Reward functions 1:27:01 – Bitter lesson by Rich Sutton 1:32:13 – Advice for students interesting in AI 1:33:55 – Meaning of life