{"total":83,"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":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"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":"2105.02993","title":"Learning Controllable Content Generators","created":"2021-05-06","cited_by_count":40,"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":"2401.05675","title":"Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation","created":"2024-01-11","cited_by_count":36,"area":"alignment"},{"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":"2508.02298","title":"CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment","created":"2025-08-04","cited_by_count":26,"area":"lr"},{"id":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2206.03378","title":"Imitating Past Successes can be Very Suboptimal","created":"2022-06-07","cited_by_count":23,"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":"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":"2205.07000","title":"PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning","created":"2022-05-14","cited_by_count":18,"area":null},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2110.15097","title":"Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning","created":"2021-10-28","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":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2208.12584","title":"Socially Fair Reinforcement Learning","created":"2022-08-26","cited_by_count":13,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2401.02244","title":"Policy-regularized Offline Multi-objective Reinforcement Learning","created":"2024-01-04","cited_by_count":10,"area":"offlinerl"},{"id":"2406.07295","title":"Multi-objective Reinforcement learning from AI Feedback","created":"2024-06-11","cited_by_count":10,"area":"alignment"},{"id":"2105.02377","title":"Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2503.13817","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","created":"2025-03-18","cited_by_count":9,"area":"mllm"},{"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":"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":"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":"1907.02140","title":"Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model","created":"2019-07-03","cited_by_count":7,"area":"offlinerl"},{"id":"2202.10630","title":"Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach","created":"2022-02-22","cited_by_count":7,"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":"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":"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":"2509.14816","title":"Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution","created":"2025-09-18","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":"2207.03029","title":"Multi-objective Optimization of Notifications Using Offline Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":"offlinerl"},{"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":"2111.09191","title":"Preference Communication in Multi-Objective Normal-Form Games","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2309.02632","title":"Deep Reinforcement Learning from Hierarchical Preference Design","created":"2023-09-06","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":"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":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2306.08044","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care","created":"2023-06-13","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":"2511.07824","title":"Multi-Objective Bilevel Learning","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2602.01271","title":"From Intents to Actions: Agentic AI in Autonomous Networks","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"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":"2606.03102","title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2110.06742","title":"A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark","created":"2021-10-13","cited_by_count":1,"area":null},{"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":"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":"2411.12433","title":"Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversity","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2502.00040","title":"Multi-Objective Reinforcement Learning for Power Grid Topology Control","created":"2025-01-27","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":"2511.08339","title":"LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"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":"2605.09094","title":"A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2302.04179","title":"A Scale-Independent Multi-Objective Reinforcement Learning with Convergence Analysis","created":"2023-02-08","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":"2308.09734","title":"A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2309.10908","title":"Multicopy Reinforcement Learning Agents","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","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":"2407.13320","title":"Deep Reinforcement Learning for Multi-Objective Optimization: Enhancing Wind Turbine Energy Generation while Mitigating Noise Emissions","created":"2024-07-18","cited_by_count":0,"area":"deeprl"},{"id":"2407.15476","title":"MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search","created":"2024-07-22","cited_by_count":0,"area":"deeprl"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"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":"2511.19885","title":"Complex Instruction Following with Diverse Style Policies in Football Games","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2605.16344","title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2609.26918","title":"On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning","created":"2026-09-22","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}