TalkRL: The Reinforcement Learning Podcast cover image

Natasha Jaques

TalkRL: The Reinforcement Learning Podcast

00:00

Is Inequity Aversion More Effective Than Inequities Aversion?

Is inequity aversion more effective than the new reward system? And is there some way that they could work together? We do have a plot in our paper or a table that does show in certain of our experiments, we exceed to the maximum obtained in the inequity aversion paper in terms of total collective reward for all the agents. But it's not a direct comparison because the amount of hyperparameter sweeping in my paper was not necessarily held constant with the previous paper. So I don't want to over-claim there.

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