{"total":27,"rows":[{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2210.15185","title":"SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering","created":"2022-10-27","cited_by_count":22,"area":null},{"id":"2304.10722","title":"Reinforcement Learning Approaches for Traffic Signal Control under Missing Data","created":"2023-04-21","cited_by_count":13,"area":null},{"id":"2305.13937","title":"Multi-agent Continual Coordination via Progressive Task Contextualization","created":"2023-05-07","cited_by_count":11,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2506.09272","title":"G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2305.05116","title":"Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2512.21586","title":"Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations","created":"2025-12-25","cited_by_count":5,"area":null},{"id":"2412.10778","title":"Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos","created":"2024-12-14","cited_by_count":4,"area":null},{"id":"2508.05441","title":"Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2309.13508","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","created":"2023-09-24","cited_by_count":2,"area":null},{"id":"2503.22249","title":"FLAM: Foundation Model-Based Body Stabilization for Humanoid Locomotion and Manipulation","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2209.08169","title":"Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2212.05572","title":"Off-Policy Deep Reinforcement Learning Algorithms for Handling Various Robotic Manipulator Tasks","created":"2022-12-11","cited_by_count":1,"area":null},{"id":"2303.05458","title":"Beware of Instantaneous Dependence in Reinforcement Learning","created":"2023-03-09","cited_by_count":1,"area":null},{"id":"2308.13654","title":"Pretty darn good control: when are approximate solutions better than approximate models","created":"2023-08-25","cited_by_count":1,"area":null},{"id":"2311.01568","title":"Anytime-Competitive Reinforcement Learning with Policy Prior","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2312.06357","title":"FOSS: A Self-Learned Doctor for Query Optimizer","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2212.02715","title":"Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learning","created":"2022-12-06","cited_by_count":0,"area":null},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2307.06501","title":"Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2401.03151","title":"Semi-supervised learning via DQN for log anomaly detection","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2502.18529","title":"Heterogeneous Decision Making in Mixed Traffic: Uncertainty-aware Planning and Bounded Rationality","created":"2025-02-25","cited_by_count":0,"area":null}],"next_cursor":null}