{"total":95,"rows":[{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2106.00467","title":"A Clarification of the Nuances in the Fairness Metrics Landscape","created":"2021-06-01","cited_by_count":98,"area":null},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2102.08410","title":"Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information","created":"2021-02-16","cited_by_count":33,"area":null},{"id":"2107.05216","title":"A Simple Reward-free Approach to Constrained Reinforcement Learning","created":"2021-07-12","cited_by_count":30,"area":null},{"id":"2205.13619","title":"Fairness in Recommendation: Foundations, Methods and Applications","created":"2022-05-26","cited_by_count":27,"area":null},{"id":"2304.09362","title":"Long-Term Fairness with Unknown Dynamics","created":"2023-04-19","cited_by_count":27,"area":null},{"id":"2110.09253","title":"A Sociotechnical View of Algorithmic Fairness","created":"2021-09-27","cited_by_count":24,"area":null},{"id":"2104.14527","title":"Online certification of preference-based fairness for personalized recommender systems","created":"2021-04-29","cited_by_count":22,"area":null},{"id":"2105.02091","title":"When Fair Ranking Meets Uncertain Inference","created":"2021-05-05","cited_by_count":22,"area":null},{"id":"2212.01382","title":"Welfare and Fairness in Multi-objective Reinforcement Learning","created":"2022-11-30","cited_by_count":20,"area":null},{"id":"2204.01819","title":"Achieving Long-Term Fairness in Sequential Decision Making","created":"2022-04-04","cited_by_count":19,"area":null},{"id":"2111.01201","title":"Unintended Selection: Persistent Qualification Rate Disparities and Interventions","created":"2021-11-01","cited_by_count":18,"area":null},{"id":"2206.04101","title":"What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective","created":"2022-06-08","cited_by_count":18,"area":null},{"id":"2110.13986","title":"Fair Sequential Selection Using Supervised Learning Models","created":"2021-10-26","cited_by_count":16,"area":null},{"id":"2103.16033","title":"FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoT","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2109.10458","title":"Achieving Counterfactual Fairness for Causal Bandit","created":"2021-09-21","cited_by_count":15,"area":null},{"id":"2302.05995","title":"Multi-dimensional discrimination in Law and Machine Learning -- A comparative overview","created":"2023-02-12","cited_by_count":15,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2111.10476","title":"Towards Return Parity in Markov Decision Processes","created":"2021-11-19","cited_by_count":13,"area":null},{"id":"2208.12584","title":"Socially Fair Reinforcement Learning","created":"2022-08-26","cited_by_count":13,"area":null},{"id":"2303.08516","title":"Fair Off-Policy Learning from Observational Data","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2101.02084","title":"Fairness with Continuous Optimal Transport","created":"2021-01-06","cited_by_count":10,"area":null},{"id":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2211.03994","title":"Reinforcement Learning with Stepwise Fairness Constraints","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2306.09995","title":"Fairness in Preference-based Reinforcement Learning","created":"2023-06-16","cited_by_count":9,"area":null},{"id":"2311.12447","title":"Designing Long-term Group Fair Policies in Dynamical Systems","created":"2023-11-21","cited_by_count":9,"area":null},{"id":"2405.06909","title":"Fairness in Reinforcement Learning: A Survey","created":"2024-05-11","cited_by_count":9,"area":"deeprl"},{"id":"2106.05727","title":"Cooperative Multi-Agent Fairness and Equivariant Policies","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2205.08875","title":"Multi-disciplinary fairness considerations in machine learning for clinical trials","created":"2022-05-18","cited_by_count":8,"area":null},{"id":"2208.09254","title":"Mitigating Disparity while Maximizing Reward: Tight Anytime Guarantee for Improving Bandits","created":"2022-08-19","cited_by_count":8,"area":null},{"id":"2312.04772","title":"Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making","created":"2023-12-08","cited_by_count":8,"area":null},{"id":"2103.01009","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2111.08221","title":"Fairness-aware Online Price Discrimination with Nonparametric Demand Models","created":"2021-11-16","cited_by_count":7,"area":null},{"id":"2301.08987","title":"Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2306.00025","title":"Disentangling and Operationalizing AI Fairness at LinkedIn","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2311.02544","title":"Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2102.07120","title":"Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environment","created":"2021-02-14","cited_by_count":6,"area":null},{"id":"2202.02790","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","created":"2022-02-06","cited_by_count":6,"area":null},{"id":"2104.12037","title":"Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instability","created":"2021-04-24","cited_by_count":5,"area":null},{"id":"2106.01325","title":"Addressing the Long-term Impact of ML Decisions via Policy Regret","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2110.14621","title":"Fairer LP-based Online Allocation via Analytic Center","created":"2021-10-27","cited_by_count":5,"area":null},{"id":"2207.13343","title":"Towards Soft Fairness in Restless Multi-Armed Bandits","created":"2022-07-27","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2502.11828","title":"Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces","created":"2025-02-17","cited_by_count":5,"area":"deeprl"},{"id":"2110.11404","title":"Statistical discrimination in learning agents","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2207.12138","title":"Towards Fairness-Aware Multi-Objective Optimization","created":"2022-07-22","cited_by_count":4,"area":null},{"id":"2310.11407","title":"Group-blind optimal transport to group parity and its constrained variants","created":"2023-10-17","cited_by_count":4,"area":null},{"id":"2401.06318","title":"Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learning","created":"2024-01-12","cited_by_count":4,"area":"deeprl"},{"id":"2406.06736","title":"Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2411.18195","title":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","created":"2024-11-27","cited_by_count":4,"area":"deeprl"},{"id":"2102.00311","title":"Fairness through Social Welfare Optimization","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2408.17313","title":"Fair Best Arm Identification with Fixed Confidence","created":"2024-08-30","cited_by_count":3,"area":null},{"id":"2110.08307","title":"GrowSpace: Learning How to Shape Plants","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2306.13440","title":"Trading-off price for data quality to achieve fair online allocation","created":"2023-06-23","cited_by_count":2,"area":null},{"id":"2408.09489","title":"REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2409.02246","title":"Multi-Agent Reinforcement Learning for Joint Police Patrol and Dispatch","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2502.03953","title":"Fairness Aware Reinforcement Learning via Proximal Policy Optimization","created":"2025-02-06","cited_by_count":2,"area":"deeprl"},{"id":"2506.11242","title":"A Causal Lens for Learning Long-term Fair Policies","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2604.21711","title":"Fairness under uncertainty in sequential decisions","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2606.18111","title":"Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning","created":"2026-06-16","cited_by_count":2,"area":"deeprl"},{"id":"2108.05315","title":"Fairness Through Counterfactual Utilities","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2108.05523","title":"Fair Decision-Making for Food Inspections","created":"2021-08-12","cited_by_count":1,"area":null},{"id":"2201.07203","title":"Emergent Instabilities in Algorithmic Feedback Loops","created":"2022-01-18","cited_by_count":1,"area":null},{"id":"2302.09298","title":"Improving Fairness in Adaptive Social Exergames via Shapley Bandits","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2307.05857","title":"FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systems","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2307.11379","title":"Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2403.19419","title":"Fairness in Ranking: Robustness through Randomization without the Protected Attribute","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2407.07350","title":"Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2412.17123","title":"Fairness in Reinforcement Learning with Bisimulation Metrics","created":"2024-12-22","cited_by_count":1,"area":"deeprl"},{"id":"2504.18897","title":"ReLU integral probability metric and its applications","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2509.16399","title":"VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping","created":"2025-09-19","cited_by_count":1,"area":"alignment"},{"id":"2111.04272","title":"Identifying Best Fair Intervention","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2201.01450","title":"Offsetting Unequal Competition through RL-assisted Incentive Schemes","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2306.04498","title":"Near-Optimal Privacy-Preserving Learning for Max-Min Fair Multi-Agent Bandits","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2311.03468","title":"FinA: Fairness of Adverse Effects in Decision-Making of Human-Cyber-Physical-System","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2402.15561","title":"Fair Multivariate Adaptive Regression Splines for Ensuring Equity and Transparency","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2407.03146","title":"Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2411.09804","title":"Fair Resource Allocation in Weakly Coupled Markov Decision Processes","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2506.10313","title":"Collaborative Min-Max Regret in Grouped Multi-Armed Bandits","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2508.14311","title":"Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.09655","title":"Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management","created":"2025-09-11","cited_by_count":0,"area":"offlinerl"},{"id":"2510.19893","title":"EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2604.04334","title":"Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications","created":"2026-04-06","cited_by_count":0,"area":"deeprl"},{"id":"2605.06227","title":"Price of Fairness in Short-Term and Long-Term Algorithmic Selections","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.22291","title":"Long-term Fairness with Selective Labels","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.01159","title":"Fairness in two-player zero-sum games with bandit feedback","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.17266","title":"SkillChain-Gym: A Benchmark for Reskilling-Aware Production-Inventory Control under Disruptions","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.30989","title":"Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.19389","title":"Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.00175","title":"Inference-Time Policy Alignment for Fair Reinforcement Learning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.09366","title":"Beyond Binary: Continuous State Optimization with Graph-Structured Objectives","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2610.15015","title":"Algorithmic Fairness Over Time: Advances & Prospects","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.20514","title":"Bayesian Learning to Select Fair Classifiers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}