TalkRL: The Reinforcement Learning Podcast cover image

Jakob Foerster

TalkRL: The Reinforcement Learning Podcast

00:00

The Prisoner's Dilemma: A Tragedy of the Commons

The prisoner's dilemma was first analyzed by a Rand Corporation in the 50s. It depicts this tragedy of the commons where it seems like the sensible thing to do is always to betray your counterpart and you both suffer. The good news is that humanity has mostly managed to turn single shot games into iterated games. That means we're playing prisoner Loma over and over again often with the same partners. And that completely changes what type of outcomes are possible amongst rational agents, among self-interested agents.

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