Socially Fair Reinforcement Learning

Abstract

We consider the problem of episodic reinforcement learning where there are multiple stakeholders with different reward functions. Our goal is to output a policy that is socially fair with respect to different reward functions. Prior works have proposed different objectives that a fair policy must optimize including minimum welfare, and generalized Gini welfare. We first take an axiomatic view of the problem, and propose four axioms that any such fair objective must satisfy. We show that the Nash social welfare is the unique objective that uniquely satisfies all four objectives, whereas prior objectives fail to satisfy all four axioms. We then consider the learning version of the problem where the underlying model i.e. Markov decision process is unknown. We consider the problem of minimizing regret with respect to the fair policies maximizing three different fair objectives -- minimum welfare, generalized Gini welfare, and Nash social welfare. Based on optimistic planning, we propose a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymandal2022socially

Related papers

• 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
• Specification-guided Learning Of Nash Equilibria With High Social Welfare (2022)0.00
• Fairness In Reinforcement Learning (2016)0.00
• What Hides Behind Unfairness? Exploring Dynamics Fairness In Reinforcement Learning (2024)0.95
• Striking A Balance In Fairness For Dynamic Systems Through Reinforcement Learning (2024)2.26
• Accommodating Picky Customers: Regret Bound And Exploration Complexity For Multi-objective Reinforcement Learning (2020)0.00
• Generalizing Across Multi-objective Reward Functions In Deep Reinforcement Learning (2018)0.00