AXRP - the AI X-risk Research Podcast cover image

3 - Negotiable Reinforcement Learning with Andrew Critch

AXRP - the AI X-risk Research Podcast

CHAPTER

I Don't Think the Harsani Aggregation Theorem Applies, Right?

The original question, i think, was, why? Why doesn't the harsani aggregation theorem apply. And it's more like, well, a, we could say in a meta in ameta problem of like fairness and co operation being two different principles you want to serve. Ah, that's pretty good for co operation and pretty good for fairness. I would say harsan's approach isis is pareto sub oftimal, because you can get more co operation, am a, but it also, you know, you should also be adding fairness, a as a constraint to her sanyy.

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