What Hides Behind Unfairness? Exploring Dynamics Fairness In Reinforcement Learning

Abstract

In sequential decision-making problems involving sensitive attributes like race and gender, reinforcement learning (RL) agents must carefully consider long-term fairness while maximizing returns. Recent works have proposed many different types of fairness notions, but how unfairness arises in RL problems remains unclear. In this paper, we address this gap in the literature by investigating the sources of inequality through a causal lens. We first analyse the causal relationships governing the data generation process and decompose the effect of sensitive attributes on long-term well-being into distinct components. We then introduce a novel notion called dynamics fairness, which explicitly captures the inequality stemming from environmental dynamics, distinguishing it from those induced by decision-making or inherited from the past. This notion requires evaluating the expected changes in the next state and the reward induced by changing the value of the sensitive attribute while holding

Stats

• citations0
• S2 citations—
• github stars2
• HF likes0
• heat score0.95
• arxiv keydeng2024what

Related papers

• Striking A Balance In Fairness For Dynamic Systems Through Reinforcement Learning (2024)2.26
• Achieving Fairness In Multi-agent Markov Decision Processes Using Reinforcement Learning (2023)0.00
• Counterfactually Fair Reinforcement Learning Via Sequential Data Preprocessing (2025)0.00
• Fairness In Reinforcement Learning (2016)0.00
• Learning Fair Policies In Multiobjective (deep) Reinforcement Learning With Average And Discounted Rewards (2020)0.00
• Socially Fair Reinforcement Learning (2022)0.00
• [re] Fairdice: A Gap Between Theory And Practice (2026)0.00
• Past-discounting Is Key For Learning Markovian Fairness With Long Horizons (2025)0.00