Group Fairness in Multi-Task Reinforcement Learning
It addresses fairness concerns in real-world multi-task RL applications, which is an incremental advance over single-task fairness methods.
This paper tackles the problem of ensuring equitable outcomes across demographic groups in multi-task reinforcement learning by introducing a novel formulation and a constrained optimization algorithm that enforces fairness constraints across multiple tasks simultaneously, demonstrating smaller fairness gaps while maintaining comparable returns in experiments.
This paper addresses a critical societal consideration in the application of Reinforcement Learning (RL): ensuring equitable outcomes across different demographic groups in multi-task settings. While previous work has explored fairness in single-task RL, many real-world applications are multi-task in nature and require policies to maintain fairness across all tasks. We introduce a novel formulation of multi-task group fairness in RL and propose a constrained optimization algorithm that explicitly enforces fairness constraints across multiple tasks simultaneously. We have shown that our proposed algorithm does not violate fairness constraints with high probability and with sublinear regret in the finite-horizon episodic setting. Through experiments in RiverSwim and MuJoCo environments, we demonstrate that our approach better ensures group fairness across multiple tasks compared to previous methods that lack explicit multi-task fairness constraints in both the finite-horizon setting and the infinite-horizon setting. Our results show that the proposed algorithm achieves smaller fairness gaps while maintaining comparable returns across different demographic groups and tasks, suggesting its potential for addressing fairness concerns in real-world multi-task RL applications.