{"total":60,"rows":[{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280,"area":"alignment"},{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256,"area":null},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2110.09253","title":"A Sociotechnical View of Algorithmic Fairness","created":"2021-09-27","cited_by_count":24,"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":"2104.14504","title":"An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning","created":"2021-04-29","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":"2406.07826","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","created":"2024-06-12","cited_by_count":15,"area":"deeprl"},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2210.12546","title":"Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems","created":"2022-10-22","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":"2204.06521","title":"Optimizing generalized Gini indices for fairness in rankings","created":"2022-04-02","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":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2306.09995","title":"Fairness in Preference-based Reinforcement Learning","created":"2023-06-16","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":"2306.00324","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","created":"2023-06-01","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":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"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":"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":"2410.15557","title":"How to Find the Exact Pareto Front for Multi-Objective MDPs?","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2510.20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","created":"2025-10-23","cited_by_count":5,"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":"2502.04281","title":"DECAF: Learning to be Fair in Multi-agent Resource Allocation","created":"2025-02-06","cited_by_count":4,"area":null},{"id":"2102.00311","title":"Fairness through Social Welfare Optimization","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2302.05740","title":"UGAE: A Novel Approach to Non-exponential Discounting","created":"2023-02-11","cited_by_count":3,"area":null},{"id":"2503.23626","title":"A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control","created":"2025-03-30","cited_by_count":3,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2401.03163","title":"An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments","created":"2024-01-06","cited_by_count":2,"area":"deeprl"},{"id":"2502.03953","title":"Fairness Aware Reinforcement Learning via Proximal Policy Optimization","created":"2025-02-06","cited_by_count":2,"area":"deeprl"},{"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":"2303.08909","title":"Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2303.09027","title":"Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning","created":"2023-03-16","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":"2402.06266","title":"Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity","created":"2024-02-09","cited_by_count":1,"area":"deeprl"},{"id":"2407.13279","title":"Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":1,"area":"deeprl"},{"id":"2412.17123","title":"Fairness in Reinforcement Learning with Bisimulation Metrics","created":"2024-12-22","cited_by_count":1,"area":"deeprl"},{"id":"2502.20957","title":"Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning","created":"2025-02-28","cited_by_count":1,"area":"deeprl"},{"id":"2504.01154","title":"Past-Discounting is Key for Learning Markovian Fairness with Long Horizons","created":"2025-04-01","cited_by_count":1,"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":"2404.08006","title":"Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2405.00410","title":"UCB-driven Utility Function Search for Multi-objective Reinforcement Learning","created":"2024-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2405.03692","title":"Imitation Learning for Adaptive Video Streaming with Future Adversarial Information Bottleneck Principle","created":"2024-03-12","cited_by_count":0,"area":"offlinerl"},{"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":"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":"2411.09804","title":"Fair Resource Allocation in Weakly Coupled Markov Decision Processes","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2506.22708","title":"FairMarket-RL: LLM-Guided Fairness Shaping for Multi-Agent Reinforcement Learning in Peer-to-Peer Markets","created":"2025-06-28","cited_by_count":0,"area":"agents"},{"id":"2510.26740","title":"A General Incentives-Based Framework for Fairness in Multi-agent Resource Allocation","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2604.02151","title":"Auction-Based Online Policy Adaptation for Evolving Objectives","created":"2026-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.01961","title":"Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare","created":"2026-05-03","cited_by_count":0,"area":"alignment"},{"id":"2605.31388","title":"Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"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":"2606.04167","title":"Smart Transportation Without Neurons -- Fair Metro Network Expansion with Tabular Reinforcement Learning","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"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}