Google DeepMind: The Podcast cover image

Life is like a game

Google DeepMind: The Podcast

CHAPTER

How to Train an Agent in a Game?

Deep mind has developed an algorithm that can teach agents how to play video games. Agents are given internal rewards based on events in the game, such as picking up a flag or dropping a flag. They then individually evolve their own intern rewards for each of these events. This kind of evolutionary group training means that they can assume different roles producing better results for stealing a flag.

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