{"total":100,"rows":[{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81,"area":"offlinerl"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"1907.13220","title":"Multi-Agent Adversarial Inverse Reinforcement Learning","created":"2019-07-30","cited_by_count":60,"area":"offlinerl"},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2202.10341","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","created":"2022-02-17","cited_by_count":49,"area":"driving"},{"id":"2006.06412","title":"Modeling Human Driving Behavior through Generative Adversarial Imitation Learning","created":"2020-06-10","cited_by_count":45,"area":"offlinerl"},{"id":"2403.12835","title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","created":"2024-03-19","cited_by_count":32,"area":"offlinerl"},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2101.03864","title":"Deep Interactive Bayesian Reinforcement Learning via Meta-Learning","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"1811.03516","title":"Learning from Demonstration in the Wild","created":"2018-11-08","cited_by_count":25,"area":"offlinerl"},{"id":"1903.05766","title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","created":"2019-03-14","cited_by_count":24,"area":"offlinerl"},{"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":"2102.04653","title":"Proximal Gradient Descent-Ascent: Variable Convergence under K{\\L} Geometry","created":"2021-02-09","cited_by_count":18,"area":null},{"id":"2102.08903","title":"Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games","created":"2021-02-17","cited_by_count":18,"area":null},{"id":"2110.04507","title":"TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2108.06038","title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","created":"2021-08-13","cited_by_count":17,"area":null},{"id":"2409.00134","title":"MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale","created":"2024-08-29","cited_by_count":17,"area":"agents"},{"id":"2310.15414","title":"Diverse Conventions for Human-AI Collaboration","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2402.18062","title":"Generative AI for Unmanned Vehicle Swarms: Challenges, Applications and Opportunities","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2006.03503","title":"Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration","created":"2020-06-05","cited_by_count":13,"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":"2103.13887","title":"Adversarial Imitation Learning with Trajectorial Augmentation and Correction","created":"2021-03-25","cited_by_count":11,"area":"offlinerl"},{"id":"2406.04219","title":"Multi-Agent Imitation Learning: Value is Easy, Regret is Hard","created":"2024-06-06","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":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2305.13030","title":"Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations","created":"2023-05-22","cited_by_count":9,"area":null},{"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":"2301.02060","title":"A first-order augmented Lagrangian method for constrained minimax optimization","created":"2023-01-05","cited_by_count":8,"area":null},{"id":"2403.17601","title":"LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation","created":"2024-03-26","cited_by_count":8,"area":"offlinerl"},{"id":"1909.11468","title":"Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems","created":"2019-09-25","cited_by_count":7,"area":"offlinerl"},{"id":"2211.03408","title":"RITA: Boost Driving Simulators with Realistic Interactive Traffic Flow","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2303.00413","title":"Automated Task-Time Interventions to Improve Teamwork using Imitation Learning","created":"2023-03-01","cited_by_count":7,"area":"offlinerl"},{"id":"2509.08221","title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","created":"2025-09-10","cited_by_count":7,"area":"driving"},{"id":"2509.14159","title":"MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies","created":"2025-09-17","cited_by_count":7,"area":"diffusion"},{"id":"1906.07374","title":"Sample-efficient Adversarial Imitation Learning from Observation","created":"2019-06-18","cited_by_count":6,"area":"offlinerl"},{"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":"2103.11845","title":"Learning to Simulate on Sparse Trajectory Data","created":"2021-03-22","cited_by_count":6,"area":null},{"id":"2302.11996","title":"K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs","created":"2023-02-23","cited_by_count":6,"area":null},{"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":"2503.20105","title":"Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations","created":"2025-03-25","cited_by_count":6,"area":"agents"},{"id":"2110.07098","title":"A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2206.00233","title":"DM$^2$: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2306.06236","title":"iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2403.08936","title":"Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning","created":"2024-03-13","cited_by_count":5,"area":null},{"id":"2506.23793","title":"Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning","created":"2025-06-30","cited_by_count":5,"area":null},{"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":"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":"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":"2206.13754","title":"DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2306.06401","title":"Long-term Microscopic Traffic Simulation with History-Masked Multi-agent Imitation Learning","created":"2023-06-10","cited_by_count":3,"area":"offlinerl"},{"id":"2401.11378","title":"Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance","created":"2024-01-21","cited_by_count":3,"area":"offlinerl"},{"id":"2409.19831","title":"Enabling Multi-Robot Collaboration from Single-Human Guidance","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2412.03959","title":"Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?","created":"2024-12-05","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":"2109.01178","title":"Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts","created":"2021-09-02","cited_by_count":2,"area":"offlinerl"},{"id":"2203.01696","title":"Fail-Safe Adversarial Generative Imitation Learning","created":"2022-03-03","cited_by_count":2,"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":"2209.08351","title":"Sample-Efficient Multi-Agent Reinforcement Learning with Demonstrations for Flocking Control","created":"2022-09-17","cited_by_count":2,"area":null},{"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":"2308.10188","title":"Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Competitive Games","created":"2023-08-20","cited_by_count":2,"area":"offlinerl"},{"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":"2311.02502","title":"MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters","created":"2023-11-04","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":"2405.19183","title":"Conditional Latent ODEs for Motion Prediction in Autonomous Driving","created":"2024-05-29","cited_by_count":2,"area":"driving"},{"id":"2502.17618","title":"Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations","created":"2025-02-24","cited_by_count":2,"area":"offlinerl"},{"id":"2503.02954","title":"Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2507.14995","title":"LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading","created":"2025-07-20","cited_by_count":2,"area":"agents"},{"id":"2510.09325","title":"Rate optimal learning of equilibria from data","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2205.07716","title":"Generalizing to New Tasks via One-Shot Compositional Subgoals","created":"2022-05-16","cited_by_count":1,"area":"offlinerl"},{"id":"2301.06864","title":"Show me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstration","created":"2023-01-17","cited_by_count":1,"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":"2302.09531","title":"AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network","created":"2023-02-19","cited_by_count":1,"area":null},{"id":"2410.15987","title":"Analyzing Closed-loop Training Techniques for Realistic Traffic Agent Models in Autonomous Highway Driving Simulations","created":"2024-10-21","cited_by_count":1,"area":"driving"},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2510.18085","title":"R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations","created":"2025-10-20","cited_by_count":1,"area":"offlinerl"},{"id":"2602.12181","title":"Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"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":"2101.03236","title":"SDA: Improving Text Generation with Self Data Augmentation","created":"2021-01-02","cited_by_count":0,"area":null},{"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":"2209.08347","title":"Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control","created":"2022-09-17","cited_by_count":0,"area":null},{"id":"2302.13124","title":"Simulation of robot swarms for learning communication-aware coordination","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2305.06924","title":"An Imitation Learning Based Algorithm Enabling Priori Knowledge Transfer in Modern Electricity Markets for Bayesian Nash Equilibrium Estimation","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2310.00964","title":"All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2404.00886","title":"MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control","created":"2024-04-01","cited_by_count":0,"area":"deeprl"},{"id":"2404.09324","title":"Mean Field Correlated Imitation Learning","created":"2024-04-14","cited_by_count":0,"area":"offlinerl"},{"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":"2512.22909","title":"A first-order method for nonconvex-strongly-concave constrained minimax optimization","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2602.21020","title":"Matching Multiple Experts: On the Exploitability of Multi-Agent Imitation Learning","created":"2026-02-24","cited_by_count":0,"area":"offlinerl"},{"id":"2604.05943","title":"MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"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"}],"next_cursor":null}