🎉Our paper is out in JAIR!
We tackle a key challenge in multi-objective reinforcement learning: how do you learn fair policies at scale when you have many conflicting objectives without requiring preference info upfront?
www.jair.org/index.php/ja...
jair.org
Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance
| Journal of Artificial Intelligence Research