TalkRL: The Reinforcement Learning Podcast cover image

Jeff Clune

TalkRL: The Reinforcement Learning Podcast

CHAPTER

The History of Random Exploration

VPT is an algorithm that can learn to do things based on what it sees in the real world. It watches YouTube videos of people playing Minecraft and learns how to get a diamond pickaxe by watching them for eight years. The system works with contractors, which doesn't cost all that much money.

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.
App store bannerPlay store banner