{"total":177,"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":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"area":null},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"area":null},{"id":"2210.08495","title":"Pareto Set Learning for Expensive Multi-Objective Optimization","created":"2022-10-16","cited_by_count":51,"area":null},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2103.13392","title":"Scalable Pareto Front Approximation for Deep Multi-Objective Learning","created":"2021-03-24","cited_by_count":45,"area":null},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","cited_by_count":36,"area":null},{"id":"2311.12495","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","created":"2023-11-21","cited_by_count":31,"area":null},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"area":null},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","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":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2508.07768","title":"Pareto Multi-Objective Alignment for Language Models","created":"2025-08-11","cited_by_count":20,"area":"alignment"},{"id":"2210.15432","title":"Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems","created":"2022-10-27","cited_by_count":19,"area":null},{"id":"2512.24138","title":"GARDO: Reinforcing Diffusion Models without Reward Hacking","created":"2025-12-30","cited_by_count":17,"area":"diffusion"},{"id":"2402.11711","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","created":"2024-02-18","cited_by_count":16,"area":"alignment"},{"id":"2206.05357","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","created":"2022-06-10","cited_by_count":15,"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":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15,"area":"deeprl"},{"id":"2208.12584","title":"Socially Fair Reinforcement Learning","created":"2022-08-26","cited_by_count":13,"area":null},{"id":"2409.15755","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","created":"2024-09-24","cited_by_count":13,"area":"deeprl"},{"id":"2307.12551","title":"Continuation Path Learning for Homotopy Optimization","created":"2023-07-24","cited_by_count":12,"area":null},{"id":"2107.11496","title":"Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings","created":"2021-07-24","cited_by_count":9,"area":null},{"id":"2203.01924","title":"Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning","created":"2022-03-03","cited_by_count":9,"area":null},{"id":"2408.12112","title":"Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards","created":"2024-08-22","cited_by_count":9,"area":"alignment"},{"id":"2503.12932","title":"Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs","created":"2025-03-17","cited_by_count":9,"area":"deeprl"},{"id":"2505.23708","title":"AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning","created":"2025-05-29","cited_by_count":9,"area":"deeprl"},{"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":"2310.03195","title":"Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions","created":"2023-10-04","cited_by_count":8,"area":null},{"id":"2401.09257","title":"A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization","created":"2024-01-17","cited_by_count":8,"area":null},{"id":"2402.12673","title":"Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies","created":"2024-02-20","cited_by_count":8,"area":"deeprl"},{"id":"2406.18924","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2408.13493","title":"Thresholded Lexicographic Ordered Multiobjective Reinforcement Learning","created":"2024-08-24","cited_by_count":8,"area":"deeprl"},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2603.00730","title":"MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning","created":"2026-02-28","cited_by_count":8,"area":null},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2307.03288","title":"Optimal Scalarizations for Sublinear Hypervolume Regret","created":"2023-07-06","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":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2505.18547","title":"Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models","created":"2025-05-24","cited_by_count":7,"area":"diffusion"},{"id":"2507.14066","title":"Preference-based Multi-Objective Reinforcement Learning","created":"2025-07-18","cited_by_count":7,"area":"deeprl"},{"id":"2106.01048","title":"Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2203.04530","title":"Design of Detectors at the Electron Ion Collider with Artificial Intelligence","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2512.11114","title":"In-Context Multi-Objective Optimization","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2211.00801","title":"Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement","created":"2022-11-02","cited_by_count":5,"area":null},{"id":"2211.13032","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2312.10194","title":"Multi-Objective Reinforcement Learning-based Approach for Pressurized Water Reactor Optimization","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2403.00282","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","created":"2024-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2405.11331","title":"Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks","created":"2024-05-18","cited_by_count":5,"area":"driving"},{"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":"2502.09724","title":"Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning","created":"2025-02-13","cited_by_count":5,"area":"deeprl"},{"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":"2106.08199","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","created":"2021-06-15","cited_by_count":4,"area":"offlinerl"},{"id":"2209.10055","title":"Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games","created":"2022-09-21","cited_by_count":4,"area":null},{"id":"2401.02160","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","created":"2024-01-04","cited_by_count":4,"area":"deeprl"},{"id":"2402.02665","title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2405.03082","title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning","created":"2024-05-05","cited_by_count":4,"area":"deeprl"},{"id":"2407.16807","title":"In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning","created":"2024-07-23","cited_by_count":4,"area":"deeprl"},{"id":"2408.15501","title":"MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning","created":"2024-08-28","cited_by_count":4,"area":"diffusion"},{"id":"2410.02236","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","created":"2024-10-03","cited_by_count":4,"area":"deeprl"},{"id":"2204.06407","title":"Flexible Multiple-Objective Reinforcement Learning for Chip Placement","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2306.06251","title":"Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks","created":"2023-06-09","cited_by_count":3,"area":null},{"id":"2308.06935","title":"Insurance pricing on price comparison websites via reinforcement learning","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2310.16487","title":"Hyperparameter Optimization for Multi-Objective Reinforcement Learning","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2407.09357","title":"Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Trees","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2502.05633","title":"Mol-MoE: Training Preference-Guided Routers for Molecule Generation","created":"2025-02-08","cited_by_count":3,"area":"moe"},{"id":"2506.16016","title":"Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations","created":"2025-06-19","cited_by_count":3,"area":"deeprl"},{"id":"2602.07764","title":"Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization","created":"2026-02-08","cited_by_count":3,"area":"deeprl"},{"id":"2108.12581","title":"Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents","created":"2021-08-28","cited_by_count":2,"area":null},{"id":"2110.08307","title":"GrowSpace: Learning How to Shape Plants","created":"2021-10-15","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":"2404.03997","title":"Demonstration Guided Multi-Objective Reinforcement Learning","created":"2024-04-05","cited_by_count":2,"area":"deeprl"},{"id":"2404.04857","title":"Demonstration-Enhanced Adaptable Multi-Objective Robot Navigation","created":"2024-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2407.11489","title":"A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments","created":"2024-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2408.09976","title":"Preference-Optimized Pareto Set Learning for Blackbox Optimization","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2504.04675","title":"HypRL: Reinforcement Learning of Control Policies for Hyperproperties","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.00787","title":"Constructing an Optimal Behavior Basis for the Option Keyboard","created":"2025-05-01","cited_by_count":2,"area":"deeprl"},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2507.19788","title":"Reinforcement Learning for Multi-Objective Multi-Echelon Supply Chain Optimisation","created":"2025-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2509.10474","title":"Generalizable Pareto-Optimal Offloading with Reinforcement Learning in Mobile Edge Computing","created":"2025-08-27","cited_by_count":2,"area":"deeprl"},{"id":"2601.20753","title":"GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning","created":"2026-01-28","cited_by_count":2,"area":"deeprl"},{"id":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.19579","title":"PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning","created":"2026-03-20","cited_by_count":2,"area":"deeprl"},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","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"}],"next_cursor":"100"}