{"total":109,"rows":[{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"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":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"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":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","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":"2209.12351","title":"Deep Reinforcement Learning for Adaptive Mesh Refinement","created":"2022-09-25","cited_by_count":20,"area":null},{"id":"2405.19650","title":"Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization","created":"2024-05-30","cited_by_count":16,"area":null},{"id":"2207.03270","title":"gym-DSSAT: a crop model turned into a Reinforcement Learning environment","created":"2022-07-07","cited_by_count":13,"area":null},{"id":"2110.12311","title":"Vector Optimization with Stochastic Bandit Feedback","created":"2021-10-23","cited_by_count":12,"area":null},{"id":"2312.11337","title":"Challenges for Reinforcement Learning in Quantum Circuit Design","created":"2023-12-18","cited_by_count":9,"area":null},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","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":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"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":"2206.13901","title":"Value Function Decomposition for Iterative Design of Reinforcement Learning Agents","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2306.03293","title":"Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning","created":"2023-06-05","cited_by_count":6,"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":"2211.00801","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":"2310.02360","title":"Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2311.11288","title":"What Lies beyond the Pareto Front? A Survey on Decision-Support Methods for Multi-Objective Optimization","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2403.17164","title":"Multi-Objective Quality-Diversity for Crystal Structure Prediction","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2312.09126","title":"Towards Trustworthy AI Software Development Assistance","created":"2023-12-14","cited_by_count":4,"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":"2503.00527","title":"Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2505.02579","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2510.03544","title":"Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2207.00368","title":"Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2207.11386","title":"Learning an Adaptive Forwarding Strategy for Mobile Wireless Networks: Resource Usage vs. Latency","created":"2022-07-23","cited_by_count":3,"area":null},{"id":"2302.05257","title":"Piecewise-Stationary Multi-Objective Multi-Armed Bandit with Application to Joint Communications and Sensing","created":"2023-02-10","cited_by_count":3,"area":null},{"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":"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":"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":"2211.01036","title":"Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2302.12668","title":"Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2305.05560","title":"Distributional Multi-Objective Decision Making","created":"2023-05-09","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":"2310.18617","title":"Pessimistic Off-Policy Multi-Objective Optimization","created":"2023-10-28","cited_by_count":2,"area":null},{"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":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2504.03715","title":"Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2505.01115","title":"Exploring Equity of Climate Policies using Multi-Agent Multi-Objective Reinforcement Learning","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2505.12049","title":"Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2505.14905","title":"Concept Incongruence: An Exploration of Time and Death in Role Playing","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2608.12679","title":"Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2204.03570","title":"Improving Urban Mobility: using artificial intelligence and new technologies to connect supply and demand","created":"2022-03-18","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":"2211.08669","title":"Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning","created":"2022-11-16","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":"2311.18703","title":"Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2312.05231","title":"Modeling Risk in Reinforcement Learning: A Literature Mapping","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2402.09486","title":"UMOEA/D: A Multiobjective Evolutionary Algorithm for Uniform Pareto Objectives based on Decomposition","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2409.15014","title":"Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2411.01008","title":"AI-Guided Codesign Framework for Novel Material and Device Design applied to MTJ-based True Random Number Generators","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2411.12433","title":"Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversity","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2503.08849","title":"Learning Pareto manifolds in high dimensions: How can regularization help?","created":"2025-03-11","cited_by_count":1,"area":null},{"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":"2509.21613","title":"Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.00220","title":"Iterative Foundation Model Fine-Tuning on Multiple Rewards","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.18181","title":"MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2512.13737","title":"Instilling Organisational Values in Firefighters through Simulation-Based Training","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2606.03471","title":"A formal definition and meta-model for a machine theory of mind","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.24042","title":"Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation","created":"2026-06-23","cited_by_count":1,"area":null},{"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":"2608.11511","title":"Let it Cook: Learning to Wait in Sequential Decision Making","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2202.07466","title":"Perspectives on risk prioritization of data center vulnerabilities using rank aggregation and multi-objective optimization","created":"2022-02-12","cited_by_count":0,"area":null},{"id":"2210.11111","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2212.03733","title":"Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior","created":"2022-12-07","cited_by_count":0,"area":null},{"id":"2212.04061","title":"Elixir: A system to enhance data quality for multiple analytics on a video stream","created":"2022-12-08","cited_by_count":0,"area":null},{"id":"2301.13799","title":"Partitioning Distributed Compute Jobs with Reinforcement Learning and Graph Neural Networks","created":"2023-01-31","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":"2310.12359","title":"MARVEL: Multi-Agent Reinforcement-Learning for Large-Scale Variable Speed Limits","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2311.10590","title":"EduGym: An Environment and Notebook Suite for Reinforcement Learning Education","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2402.11653","title":"Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing","created":"2024-02-18","cited_by_count":0,"area":null},{"id":"2405.07621","title":"Towards Adaptive IMFs -- Generalization of utility functions in Multi-Agent Frameworks","created":"2024-05-13","cited_by_count":0,"area":null},{"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":"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":"2410.02303","title":"Semantic Communication and Control Co-Design for Multi-Objective Distinct Dynamics","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2410.21882","title":"Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2411.00156","title":"Unlocking the Potential of Global Human Expertise","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2411.00563","title":"Simulate and Optimise: A two-layer mortgage simulator for designing novel mortgage assistance products","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2504.01174","title":"Value Iteration for Learning Concurrently Executable Robotic Control Tasks","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.15304","title":"AI Agents and Hard Choices","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2510.25504","title":"Multi-Objective Search: Algorithms, Applications, and Emerging Directions","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2512.18309","title":"Embedded Safety-Aligned Intelligence via Differentiable Internal Alignment Embeddings","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2603.02628","title":"Post Hoc Extraction of Pareto Fronts for Continuous Control","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.03562","title":"When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling","created":"2026-04-04","cited_by_count":0,"area":null},{"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":"2605.13647","title":"FlowCompile: An Optimizing Compiler for Structured LLM Workflows","created":"2026-05-13","cited_by_count":0,"area":null},{"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}],"next_cursor":"100"}