{"total":34,"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":"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":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"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":"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":"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":"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":"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":"2207.05886","title":"Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior","created":"2022-07-12","cited_by_count":4,"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":"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":"2306.09445","title":"Utility Theory based Cognitive Modeling in the Application of Robotics: A Survey","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2402.03540","title":"Regulation Games for Trustworthy Machine Learning","created":"2024-02-05","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":"2502.08542","title":"Beyond Predictions: A Participatory Framework for Multi-Stakeholder Decision-Making","created":"2025-02-12","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":"2106.12704","title":"All unconstrained strongly convex problems are weakly simplicial","created":"2021-06-24","cited_by_count":1,"area":null},{"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":"2204.03570","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":"2308.16889","title":"Federated Learning in UAV-Enhanced Networks: Joint Coverage and Convergence Time Optimization","created":"2023-08-31","cited_by_count":1,"area":null},{"id":"2605.06864","title":"Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization","created":"2026-05-07","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":"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":"2401.05572","title":"Innate-Values-driven Reinforcement Learning based Cooperative Multi-Agent Cognitive Modeling","created":"2024-01-10","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":"2505.09756","title":"LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2508.14705","title":"Learning in Repeated Multi-Objective Stackelberg Games with Payoff Manipulation","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2601.00329","title":"Sparse Probabilistic Coalition Structure Generation: Bayesian Greedy Pursuit and $\\ell_1$ Relaxations","created":"2026-01-01","cited_by_count":0,"area":null},{"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":"2607.09298","title":"Risk-Aware General-Utility Markov Decision Processes","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}