{"total":134,"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":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"area":null},{"id":"2308.13724","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","created":"2023-08-26","cited_by_count":77,"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":"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":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"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":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2212.13769","title":"Lexicographic Multi-Objective Reinforcement Learning","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"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":"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":"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":"2205.01423","title":"Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2605.20164","title":"Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2312.15127","title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2102.01353","title":"Subdimensional Expansion for Multi-objective Multi-agent Path Finding","created":"2021-02-02","cited_by_count":9,"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":"2102.10362","title":"Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs","created":"2021-02-20","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":"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":"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":"2406.18924","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","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":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2108.00710","title":"Multi-Objective Path-Based D* Lite","created":"2021-08-02","cited_by_count":7,"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":"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":"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":"2307.03288","title":"Optimal Scalarizations for Sublinear Hypervolume Regret","created":"2023-07-06","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":"2205.07767","title":"Efficient Algorithms for Planning with Participation Constraints","created":"2022-05-16","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":"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":"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":"2102.00966","title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search","created":"2021-02-01","cited_by_count":5,"area":null},{"id":"2103.14600","title":"Model-Free Learning of Safe yet Effective Controllers","created":"2021-03-26","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":"2212.12154","title":"Online Planning for Constrained POMDPs with Continuous Spaces through Dual Ascent","created":"2022-12-23","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":"2408.06512","title":"Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction","created":"2024-08-12","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":"2509.19358","title":"Benchmarking and Improving LLM Robustness for Personalized Generation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2102.12307","title":"Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2111.09191","title":"Preference Communication in Multi-Objective Normal-Form Games","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2203.16275","title":"Reinforcement Learning Guided by Provable Normative Compliance","created":"2022-03-30","cited_by_count":3,"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":"2209.12267","title":"Probabilistic Planning with Partially Ordered Preferences over Temporal Goals","created":"2022-09-25","cited_by_count":3,"area":null},{"id":"2305.11774","title":"Multi-objective optimisation via the R2 utilities","created":"2023-05-19","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":"2404.13954","title":"A survey of air combat behavior modeling using machine learning","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2101.11967","title":"Exploring the Impact of Tunable Agents in Sequential Social Dilemmas","created":"2021-01-28","cited_by_count":2,"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":"2204.06608","title":"Modularity benefits reinforcement learning agents with competing homeostatic drives","created":"2022-04-13","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":"2307.14346","title":"Multi-objective Deep Reinforcement Learning for Mobile Edge Computing","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2501.05591","title":"Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2505.17869","title":"Best Group Identification in Multi-Objective Bandits","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2506.21887","title":"Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2509.23095","title":"Causally-Enhanced Reinforcement Policy Optimization","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2201.00236","title":"Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning","created":"2022-01-01","cited_by_count":1,"area":null},{"id":"2202.04224","title":"Intelligent Autonomous Intersection Management","created":"2022-02-09","cited_by_count":1,"area":null},{"id":"2203.01298","title":"Pareto Frontier Approximation Network (PA-Net) to Solve Bi-objective TSP","created":"2022-03-02","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":"2211.04108","title":"Determining Accessible Sidewalk Width by Extracting Obstacle Information from Point Clouds","created":"2022-11-08","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":"2304.03773","title":"Safe Explicable Planning","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2308.09733","title":"Intrinsically Motivated Hierarchical Policy Learning in Multi-objective Markov Decision Processes","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2310.11798","title":"Auction-Based Scheduling","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2403.17358","title":"Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2405.10221","title":"Scalarisation-based risk concepts for robust multi-objective optimisation","created":"2024-05-16","cited_by_count":1,"area":null},{"id":"2406.00779","title":"Differentiation of Multi-objective Data-driven Decision Pipeline","created":"2024-06-02","cited_by_count":1,"area":null},{"id":"2412.08911","title":"Goal-Conditioned Supervised Learning for Multi-Objective Recommendation","created":"2024-12-12","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":"2601.11924","title":"Communication-Corruption Coupling and Verification in Cooperative Multi-Objective Bandits","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2601.22350","title":"Learning Policy Representations for Steerable Behavior Synthesis","created":"2026-01-29","cited_by_count":1,"area":null},{"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":"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":"2206.14081","title":"Linear programming-based solution methods for constrained partially observable Markov decision processes","created":"2022-06-28","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":"2210.11259","title":"Safe Policy Improvement in Constrained Markov Decision Processes","created":"2022-10-20","cited_by_count":0,"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":"2308.00629","title":"Dependency Structure Search Bayesian Optimization for Decision Making Models","created":"2023-08-01","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":"2312.03006","title":"Multi-Weight Ranking for Multi-Criteria Decision Making","created":"2023-12-04","cited_by_count":0,"area":null}],"next_cursor":"100"}