{"total":100,"rows":[{"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":"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":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"area":null},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55,"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":"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":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"area":null},{"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":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"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":"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":"2208.12584","title":"Socially Fair Reinforcement Learning","created":"2022-08-26","cited_by_count":13,"area":null},{"id":"2202.12028","title":"Evolutionary Multi-Objective Reinforcement Learning Based Trajectory Control and Task Offloading in UAV-Assisted Mobile Edge Computing","created":"2022-02-24","cited_by_count":11,"area":null},{"id":"2204.05027","title":"Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning","created":"2022-04-11","cited_by_count":9,"area":null},{"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":"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":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2406.18924","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","created":"2024-06-27","cited_by_count":8,"area":null},{"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":"2110.02792","title":"Hierarchical Potential-based Reward Shaping from Task Specifications","created":"2021-10-06","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":"2407.16312","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2412.01566","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","created":"2024-12-02","cited_by_count":6,"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":"2409.09958","title":"An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-09-16","cited_by_count":5,"area":"deeprl"},{"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":"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":"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":"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":"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":"2504.09906","title":"Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming","created":"2025-04-14","cited_by_count":4,"area":"moe"},{"id":"2304.14115","title":"Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach","created":"2023-04-27","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":"2506.16016","title":"Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations","created":"2025-06-19","cited_by_count":3,"area":"deeprl"},{"id":"2510.21153","title":"Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design","created":"2025-10-24","cited_by_count":3,"area":"diffusion"},{"id":"2203.04579","title":"Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2206.00270","title":"Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation","created":"2022-06-01","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":"2401.07722","title":"Inferring Preferences from Demonstrations in Multi-Objective Residential Energy Management","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2404.03997","title":"Demonstration Guided Multi-Objective Reinforcement Learning","created":"2024-04-05","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":"2501.13604","title":"FedPref: Federated Learning Across Heterogeneous Multi-objective Preferences","created":"2025-01-23","cited_by_count":2,"area":null},{"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":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2606.30997","title":"A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management","created":"2026-06-30","cited_by_count":2,"area":"moe"},{"id":"2204.04988","title":"gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach","created":"2022-04-11","cited_by_count":1,"area":null},{"id":"2209.13224","title":"Regularized Soft Actor-Critic for Behavior Transfer Learning","created":"2022-09-27","cited_by_count":1,"area":"offlinerl"},{"id":"2211.04813","title":"Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning","created":"2022-11-09","cited_by_count":1,"area":null},{"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":"2304.03365","title":"Decision-Focused Model-based Reinforcement Learning for Reward Transfer","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2307.05834","title":"Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing","created":"2023-07-11","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":"2409.20258","title":"Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning","created":"2024-09-30","cited_by_count":1,"area":"deeprl"},{"id":"2410.04719","title":"Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning","created":"2024-10-07","cited_by_count":1,"area":"deeprl"},{"id":"2410.12062","title":"MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation","created":"2024-10-15","cited_by_count":1,"area":"deeprl"},{"id":"2411.12433","title":"Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversity","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2412.03715","title":"PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning","created":"2024-12-04","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":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2602.14926","title":"MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design","created":"2026-02-16","cited_by_count":1,"area":"agents"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2603.22813","title":"Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.08946","title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","created":"2026-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2605.10585","title":"Controllability in preference-conditioned multi-objective reinforcement learning","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.12561","title":"Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2608.04999","title":"ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2210.11259","title":"Safe Policy Improvement in Constrained Markov Decision Processes","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2305.14377","title":"Unsupervised Discovery of Continuous Skills on a Sphere","created":"2023-05-21","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":"2406.11984","title":"Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2505.10803","title":"Developing and Integrating Trust Modeling into Multi-Objective Reinforcement Learning for Intelligent Agricultural Management","created":"2025-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2505.13726","title":"Benchmarking MOEAs for solving continuous multi-objective RL problems","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2506.04022","title":"Interpretability by Design for Efficient Multi-Objective Reinforcement Learning","created":"2025-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2509.06490","title":"MORSE: Multi-Objective Reinforcement Learning via Strategy Evolution for Supply Chain Optimization","created":"2025-09-08","cited_by_count":0,"area":"deeprl"},{"id":"2509.19846","title":"BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management","created":"2025-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2511.16476","title":"Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.08696","title":"Enabling Population-Based Architectures for Neural Combinatorial Optimization","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.14092","title":"Optimizing Energy and Data Collection in UAV-aided IoT Networks using Attention-based Multi-Objective Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2603.02628","title":"Post Hoc Extraction of Pareto Fronts for Continuous Control","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.03454","title":"[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2603.21988","title":"TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning","created":"2026-03-23","cited_by_count":0,"area":"deeprl"},{"id":"2604.10664","title":"Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.12771","title":"Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.31388","title":"Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.14693","title":"Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.00642","title":"Coachable agents for interactive gameplay","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.16542","title":"From Optimal Policies to Individual Differences: Rethinking Reinforcement Learning for Biology","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.18286","title":"Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.22774","title":"CC-AOS: Cost- and Horizon-Conditioned Amortized Backward Induction for Finite-Horizon Optimal Stopping","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.07180","title":"Momba: Network Modernization Improves Multi-Objective Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2608.14963","title":"Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning","created":"2026-08-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.25723","title":"It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.05819","title":"Transporting Unsecured Stacked Payloads with a Quadrupedal Robot via Multi-Objective Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}