TalkRL: The Reinforcement Learning Podcast cover image

Jordan Terry

TalkRL: The Reinforcement Learning Podcast

00:00

Dos, How Does Reward Work in Pettings?

Inpetting zoo doesn't formalize the notion of teams. Every single agent is trying to maximize, on discountedaexpected kind of future award. On whether or noton this process is co operative or competitive or mixed sum depends on the rewards present in the environment. And so penny, who doesn't formally delineate any of the stuff, giv sugist a side effect on the environment, so to speak. In pettings, wo agents can be named. If you really need to do team agent stuff, you can use agent names,. But we don't have a formal notion of support for teams, as far as reward goes.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app