{"total":11,"rows":[{"id":"2306.09995","title":"Fairness in Preference-based Reinforcement Learning","created":"2023-06-16","cited_by_count":9,"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":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"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":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2408.00682","title":"Learning in Multi-Objective Public Goods Games with Non-Linear Utilities","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2408.11822","title":"State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Survey","created":"2024-08-03","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":"2608.00175","title":"Inference-Time Policy Alignment for Fair Reinforcement Learning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.36174","title":"Fair Policy Optimization in Major-Minor Weakly Coupled Markov Decision Processes","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}