Google DeepMind: The Podcast cover image

Better together

Google DeepMind: The Podcast

CHAPTER

How to Train Pigeons to Co-Operate

Doner prekup is head of deep mines montreal office, and has spent decades refining the technique of reinforcement learning. It's behind many of deep mind's major break throughs in recent years, including alpago's victory over a human player in the game of go. The idea of using rewards originates really from psychology and animal learning theory where people thougt that rewards are a gedway for animals to learn how to perform certain tasks. In humans, this is what psychologists call our social value orientation. And optimizing for co operation in this way marks a subtle in the history of ai. Heis tore grapl again.

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