no code implementations • 23 May 2024 • Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu
The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory.
no code implementations • 15 Jul 2021 • Rupert Freeman, Evi Micha, Nisarg Shah
We introduce a new model for two-sided matching which allows us to borrow popular fairness notions from the fair division literature such as envy-freeness up to one good and maximin share guarantee.
no code implementations • NeurIPS 2021 • Safwan Hossain, Evi Micha, Nisarg Shah
Unlike the classical multi-armed bandit problem, the goal is not to learn the "best arm"; indeed, each agent may perceive a different arm to be the best for her personally.