FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning
This addresses the challenge of achieving fairness in offline MORL for applications requiring equitable resource allocation, though it is incremental as it extends distribution correction estimation to a new setting.
The paper tackled the problem of optimizing fairness-oriented goals like Nash social welfare in offline multi-objective reinforcement learning, where existing methods rely on linear scalarization and lack a unified approach for nonlinear criteria. The result was FairDICE, a framework that demonstrated strong fairness-aware performance across multiple offline benchmarks without needing explicit preference weights.
Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valued returns into scalar signals. While effective for certain preferences, this approach cannot capture fairness-oriented goals such as Nash social welfare or max-min fairness, which require nonlinear and non-additive trade-offs. Although several online algorithms have been proposed for specific fairness objectives, a unified approach for optimizing nonlinear welfare criteria in the offline setting-where learning must proceed from a fixed dataset-remains unexplored. In this work, we present FairDICE, the first offline MORL framework that directly optimizes nonlinear welfare objective. FairDICE leverages distribution correction estimation to jointly account for welfare maximization and distributional regularization, enabling stable and sample-efficient learning without requiring explicit preference weights or exhaustive weight search. Across multiple offline benchmarks, FairDICE demonstrates strong fairness-aware performance compared to existing baselines.