
Upside-Down Reinforcement Learning with Jürgen Schmidhuber - #357
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Unlocking Reinforcement Learning
This chapter explores the nuances of reinforcement learning, emphasizing the adaptation of commands based on received rewards to enhance learning. It introduces the concept of upside-down reinforcement learning within a supervised framework, showcasing methods for binary supervision and the potential for improved outcomes through deep learning.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.