Fairness In Reinforcement Learning

Abstract

We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fair polynomial time algorithm under an approximate notion of fairness, thus establishing an exponential gap between exact and approximate fairness

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjabbari2016fairness

Related papers

• What Hides Behind Unfairness? Exploring Dynamics Fairness In Reinforcement Learning (2024)0.95
• Achieving Fairness In Multi-agent Markov Decision Processes Using Reinforcement Learning (2023)0.00
• Learning Fair Policies In Multiobjective (deep) Reinforcement Learning With Average And Discounted Rewards (2020)0.00
• Striking A Balance In Fairness For Dynamic Systems Through Reinforcement Learning (2024)2.26
• Socially Fair Reinforcement Learning (2022)0.00
• Past-discounting Is Key For Learning Markovian Fairness With Long Horizons (2025)0.00
• Counterfactually Fair Reinforcement Learning Via Sequential Data Preprocessing (2025)0.00
• [re] Fairdice: A Gap Between Theory And Practice (2026)0.00