<ul><li>FairDICE is a new framework for Fairness-Driven Offline Multi-Objective Reinforcement Learning.</li><li>It aims to optimize policies in the presence of conflicting objectives by directly optimizing nonlinear welfare objectives.</li><li>FairDICE uses distribution correction estimation to account for welfare maximization and distributional regularization.</li><li>It shows strong fairness-aware performance across multiple offline benchmarks compared to existing baselines.</li></ul>

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Discover more