{"total":60,"rows":[{"id":"2006.06412","title":"Modeling Human Driving Behavior through Generative Adversarial Imitation Learning","created":"2020-06-10","cited_by_count":45,"area":"offlinerl"},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2206.13035","title":"A General Recipe for Likelihood-free Bayesian Optimization","created":"2022-06-27","cited_by_count":19,"area":null},{"id":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"area":"offlinerl"},{"id":"2107.04750","title":"Multi-Agent Imitation Learning with Copulas","created":"2021-07-10","cited_by_count":13,"area":"offlinerl"},{"id":"2201.01448","title":"Conditional Imitation Learning for Multi-Agent Games","created":"2022-01-05","cited_by_count":13,"area":"offlinerl"},{"id":"2302.10238","title":"Multiagent Inverse Reinforcement Learning via Theory of Mind Reasoning","created":"2023-02-20","cited_by_count":11,"area":"offlinerl"},{"id":"2202.06401","title":"Individual-Level Inverse Reinforcement Learning for Mean Field Games","created":"2022-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2104.14654","title":"Adversarial Inverse Reinforcement Learning for Mean Field Games","created":"2021-04-29","cited_by_count":8,"area":"offlinerl"},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2203.08015","title":"On-the-fly Strategy Adaptation for ad-hoc Agent Coordination","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2002.10525","title":"Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic","created":"2020-02-24","cited_by_count":6,"area":"offlinerl"},{"id":"2102.11905","title":"Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2103.04289","title":"Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data","created":"2021-03-07","cited_by_count":6,"area":"driving"},{"id":"2405.16439","title":"Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds","created":"2024-05-26","cited_by_count":6,"area":"offlinerl"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2206.11338","title":"Synthetic Data-Based Simulators for Recommender Systems: A Survey","created":"2022-06-22","cited_by_count":5,"area":null},{"id":"2306.08232","title":"Curricular Subgoals for Inverse Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2510.06913","title":"DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning","created":"2025-10-08","cited_by_count":5,"area":"offlinerl"},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2112.15364","title":"Robust Entropy-regularized Markov Decision Processes","created":"2021-12-31","cited_by_count":4,"area":"offlinerl"},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2411.15046","title":"On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning","created":"2024-11-22","cited_by_count":4,"area":"offlinerl"},{"id":"2505.17610","title":"Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning","created":"2025-05-23","cited_by_count":4,"area":"offlinerl"},{"id":"2102.06854","title":"Equilibrium Inverse Reinforcement Learning for Ride-hailing Vehicle Network","created":"2021-02-13","cited_by_count":3,"area":null},{"id":"2203.07092","title":"The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications","created":"2022-03-14","cited_by_count":3,"area":null},{"id":"2211.06967","title":"Identifying Coordination in a Cognitive Radar Network -- A Multi-Objective Inverse Reinforcement Learning Approach","created":"2022-11-13","cited_by_count":3,"area":"offlinerl"},{"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":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2502.14160","title":"Efficient Inverse Multiagent Learning","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2505.18595","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","created":"2025-05-24","cited_by_count":3,"area":"agents"},{"id":"2509.03845","title":"Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables","created":"2025-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2205.02959","title":"Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations","created":"2022-05-05","cited_by_count":2,"area":"offlinerl"},{"id":"2210.16915","title":"Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games","created":"2022-10-30","cited_by_count":2,"area":"offlinerl"},{"id":"2305.10548","title":"Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2310.06801","title":"Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning","created":"2023-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2402.15821","title":"Cooperation and Control in Delegation Games","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2402.19128","title":"ARMCHAIR: integrated inverse reinforcement learning and model predictive control for human-robot collaboration","created":"2024-02-29","cited_by_count":2,"area":"offlinerl"},{"id":"2502.17618","title":"Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations","created":"2025-02-24","cited_by_count":2,"area":"offlinerl"},{"id":"2510.09325","title":"Rate optimal learning of equilibria from data","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2301.08015","title":"Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2508.06832","title":"Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2509.23135","title":"Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm","created":"2025-09-27","cited_by_count":1,"area":"offlinerl"},{"id":"2602.22810","title":"Multi-agent imitation learning with function approximation: Linear Markov games and beyond","created":"2026-02-26","cited_by_count":1,"area":"offlinerl"},{"id":"2205.11163","title":"Learning to Advise and Learning from Advice in Cooperative Multi-Agent Reinforcement Learning","created":"2022-05-23","cited_by_count":0,"area":null},{"id":"2208.09611","title":"Weighted Maximum Entropy Inverse Reinforcement Learning","created":"2022-08-20","cited_by_count":0,"area":"offlinerl"},{"id":"2306.10407","title":"FP-IRL: Fokker--Planck Inverse Reinforcement Learning -- A Physics-Constrained Approach to Markov Decision Processes","created":"2023-06-17","cited_by_count":0,"area":"offlinerl"},{"id":"2404.09324","title":"Mean Field Correlated Imitation Learning","created":"2024-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2409.14542","title":"Distributionally Robust Inverse Reinforcement Learning for Identifying Multi-Agent Coordinated Sensing","created":"2024-09-22","cited_by_count":0,"area":"offlinerl"},{"id":"2503.04679","title":"Multi-Agent Inverse Q-Learning from Demonstrations","created":"2025-03-06","cited_by_count":0,"area":"alignment"},{"id":"2503.08883","title":"Imitation Learning of Correlated Policies in Stackelberg Games","created":"2025-03-11","cited_by_count":0,"area":"offlinerl"},{"id":"2509.08257","title":"Symmetry-Guided Multi-Agent Inverse Reinforcement Learning","created":"2025-09-10","cited_by_count":0,"area":"offlinerl"},{"id":"2511.05640","title":"Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2601.17678","title":"DIML: Differentiable Inverse Mechanism Learning from Behaviors of Multi-Agent Learning Trajectories","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.25199","title":"TacSIm: A Dataset and Benchmark for Football Tactical Style Imitation","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.08131","title":"Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization","created":"2026-05-01","cited_by_count":0,"area":"offlinerl"},{"id":"2605.12000","title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","created":"2026-05-12","cited_by_count":0,"area":"offlinerl"},{"id":"2607.19531","title":"Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States","created":"2026-07-21","cited_by_count":0,"area":null}],"next_cursor":null}