{"total":115,"rows":[{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290,"area":"wm"},{"id":"2502.08691","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","created":"2025-02-12","cited_by_count":186,"area":"wm"},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82,"area":"agents"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2401.00211","title":"Open-TI: Open Traffic Intelligence with Augmented Language Model","created":"2023-12-30","cited_by_count":38,"area":null},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2308.14284","title":"Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning","created":"2023-08-28","cited_by_count":36,"area":null},{"id":"2110.13827","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","created":"2021-10-26","cited_by_count":33,"area":null},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32,"area":"driving"},{"id":"2112.10107","title":"Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control","created":"2021-12-19","cited_by_count":29,"area":null},{"id":"2406.13945","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","created":"2024-06-20","cited_by_count":27,"area":"wm"},{"id":"2311.11056","title":"Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Driving","created":"2023-11-18","cited_by_count":26,"area":null},{"id":"2112.02336","title":"Efficient Pressure: Improving efficiency for signalized intersections","created":"2021-12-04","cited_by_count":24,"area":null},{"id":"2203.07676","title":"An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2211.10649","title":"LibSignal: An Open Library for Traffic Signal Control","created":"2022-11-19","cited_by_count":16,"area":null},{"id":"2503.11739","title":"CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control","created":"2025-03-14","cited_by_count":15,"area":"agents"},{"id":"2504.21048","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","created":"2025-04-29","cited_by_count":14,"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":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2208.06646","title":"Modeling Network-level Traffic Flow Transitions on Sparse Data","created":"2022-08-13","cited_by_count":12,"area":null},{"id":"2109.05491","title":"DynSTGAT: Dynamic Spatial-Temporal Graph Attention Network for Traffic Signal Control","created":"2021-09-12","cited_by_count":11,"area":null},{"id":"2204.12190","title":"Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method","created":"2022-04-26","cited_by_count":10,"area":null},{"id":"2206.11996","title":"The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality","created":"2022-06-23","cited_by_count":9,"area":null},{"id":"2305.15743","title":"TransWorldNG: Traffic Simulation via Foundation Model","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2306.11551","title":"IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2101.00746","title":"MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control","created":"2021-01-04","cited_by_count":8,"area":null},{"id":"2105.09560","title":"Objective-aware Traffic Simulation via Inverse Reinforcement Learning","created":"2021-05-20","cited_by_count":8,"area":"offlinerl"},{"id":"2206.02583","title":"Consensus Learning for Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2302.00521","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","created":"2023-02-01","cited_by_count":8,"area":"offlinerl"},{"id":"2109.05225","title":"Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting","created":"2021-09-11","cited_by_count":7,"area":null},{"id":"2201.00006","title":"Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization","created":"2021-12-30","cited_by_count":7,"area":null},{"id":"2306.07553","title":"DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2308.06931","title":"FusionPlanner: A Multi-task Motion Planner for Mining Trucks via Multi-sensor Fusion","created":"2023-08-14","cited_by_count":7,"area":null},{"id":"2103.11845","title":"Learning to Simulate on Sparse Trajectory Data","created":"2021-03-22","cited_by_count":6,"area":null},{"id":"2210.00896","title":"CBLab: Supporting the Training of Large-scale Traffic Control Policies with Scalable Traffic Simulation","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2303.11899","title":"Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning","created":"2023-03-21","cited_by_count":6,"area":null},{"id":"2305.13960","title":"From Model-Based to Data-Driven Simulation: Challenges and Trends in Autonomous Driving","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2404.03869","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2104.10917","title":"Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem","created":"2021-04-22","cited_by_count":5,"area":null},{"id":"2112.08702","title":"Learning to Share in Multi-Agent Reinforcement Learning","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2201.02381","title":"Offline Reinforcement Learning for Road Traffic Control","created":"2022-01-07","cited_by_count":5,"area":"offlinerl"},{"id":"2404.11014","title":"Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs","created":"2024-04-17","cited_by_count":5,"area":null},{"id":"2408.09768","title":"MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2505.19532","title":"Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning","created":"2025-05-26","cited_by_count":5,"area":"deeprl"},{"id":"2104.05931","title":"Two-stage training algorithm for AI robot soccer","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2402.06127","title":"CityFlowER: An Efficient and Realistic Traffic Simulator with Embedded Machine Learning Models","created":"2024-02-09","cited_by_count":4,"area":null},{"id":"2408.09588","title":"SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras","created":"2024-08-18","cited_by_count":4,"area":null},{"id":"2409.12001","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","created":"2024-09-18","cited_by_count":4,"area":"offlinerl"},{"id":"2410.22938","title":"DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data","created":"2024-10-30","cited_by_count":4,"area":"diffusion"},{"id":"2412.20519","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","created":"2024-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2110.15926","title":"Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2202.09773","title":"Learning to Help Emergency Vehicles Arrive Faster: A Cooperative Vehicle-Road Scheduling Approach","created":"2022-02-20","cited_by_count":3,"area":null},{"id":"2205.00427","title":"TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources","created":"2022-05-01","cited_by_count":3,"area":null},{"id":"2205.13836","title":"Feudal Multi-Agent Reinforcement Learning with Adaptive Network Partition for Traffic Signal Control","created":"2022-05-27","cited_by_count":3,"area":null},{"id":"2303.14646","title":"A Survey of Machine Learning-Based Ride-Hailing Planning","created":"2023-03-26","cited_by_count":3,"area":null},{"id":"2304.03697","title":"HumanLight: Incentivizing Ridesharing via Human-centric Deep Reinforcement Learning in Traffic Signal Control","created":"2023-04-05","cited_by_count":3,"area":null},{"id":"2307.12388","title":"Uncertainty-aware Grounded Action Transformation towards Sim-to-Real Transfer for Traffic Signal Control","created":"2023-07-23","cited_by_count":3,"area":null},{"id":"2403.06884","title":"A Simple Framework Towards Vision-based Traffic Signal Control with Microscopic Simulation","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2403.17328","title":"Learning Traffic Signal Control via Genetic Programming","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2403.17533","title":"BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat","created":"2024-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2411.06601","title":"OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control","created":"2024-11-10","cited_by_count":3,"area":"offlinerl"},{"id":"2502.20065","title":"RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles","created":"2025-02-27","cited_by_count":3,"area":"driving"},{"id":"2503.23626","title":"A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control","created":"2025-03-30","cited_by_count":3,"area":null},{"id":"2508.16090","title":"GPLight+: A Genetic Programming Method for Learning Symmetric Traffic Signal Control Policy","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2510.15365","title":"TranSimHub:A Unified Air-Ground Simulation Platform for Multi-Modal Perception and Decision-Making","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2512.20996","title":"TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control","created":"2025-12-24","cited_by_count":3,"area":"agents"},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2210.14524","title":"A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2303.07046","title":"Deploying Offline Reinforcement Learning with Human Feedback","created":"2023-03-13","cited_by_count":2,"area":"alignment"},{"id":"2303.10828","title":"DataLight: Offline Data-Driven Traffic Signal Control","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2505.07257","title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","created":"2025-05-12","cited_by_count":2,"area":"wm"},{"id":"2506.06999","title":"Towards Physics-informed Diffusion for Anomaly Detection in Trajectories","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2508.20818","title":"cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending","created":"2025-08-28","cited_by_count":2,"area":"agents"},{"id":"2511.00136","title":"A Dual Large Language Models Architecture with Herald Guided Prompts for Parallel Fine Grained Traffic Signal Control","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2109.07180","title":"Back to Basics: Deep Reinforcement Learning in Traffic Signal Control","created":"2021-09-15","cited_by_count":1,"area":null},{"id":"2206.09590","title":"From Multi-agent to Multi-robot: A Scalable Training and Evaluation Platform for Multi-robot Reinforcement Learning","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2211.01025","title":"DynamicLight: Two-Stage Dynamic Traffic Signal Timing","created":"2022-11-02","cited_by_count":1,"area":null},{"id":"2303.03395","title":"Demonstration-guided Deep Reinforcement Learning for Coordinated Ramp Metering and Perimeter Control in Large Scale Networks","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2306.08843","title":"Real-Time Network-Level Traffic Signal Control: An Explicit Multiagent Coordination Method","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2311.04239","title":"Kindness in Multi-Agent Reinforcement Learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2311.15920","title":"A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning","created":"2023-11-27","cited_by_count":1,"area":"offlinerl"},{"id":"2408.15538","title":"TrafficGamer: Reliable and Flexible Traffic Simulation for Safety-Critical Scenarios with Game-Theoretic Oracles","created":"2024-08-28","cited_by_count":1,"area":"driving"},{"id":"2410.18202","title":"PyTSC: A Unified Platform for Multi-Agent Reinforcement Learning in Traffic Signal Control","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2502.13248","title":"Communication Strategy on Macro-and-Micro Traffic State in Cooperative Deep Reinforcement Learning for Regional Traffic Signal Control","created":"2025-02-18","cited_by_count":1,"area":"deeprl"},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2511.19253","title":"MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2511.23122","title":"Evolutionary Discovery of Heuristic Policies for Traffic Signal Control","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2105.08279","title":"Learning to Route via Theory-Guided Residual Network","created":"2021-05-18","cited_by_count":0,"area":null},{"id":"2202.10612","title":"A Decentralized Communication Framework based on Dual-Level Recurrence for Multi-Agent Reinforcement Learning","created":"2022-02-22","cited_by_count":0,"area":null},{"id":"2204.03471","title":"DynLight: Realize dynamic phase duration with multi-level traffic signal control","created":"2022-04-07","cited_by_count":0,"area":null},{"id":"2306.09662","title":"Cooperative Multi-Objective Reinforcement Learning for Traffic Signal Control and Carbon Emission Reduction","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2311.08429","title":"Purpose in the Machine: Do Traffic Simulators Produce Distributionally Equivalent Outcomes for Reinforcement Learning Applications?","created":"2023-11-14","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":"2406.10661","title":"A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2501.02548","title":"Planning Under Observation Mismatch for Traffic Signal Control via Adaptive Modular World Models","created":"2025-01-05","cited_by_count":0,"area":"wm"},{"id":"2502.11937","title":"FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control","created":"2025-02-17","cited_by_count":0,"area":"offlinerl"},{"id":"2504.18010","title":"Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future Transportation","created":"2025-04-25","cited_by_count":0,"area":"driving"},{"id":"2505.12109","title":"SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces","created":"2025-05-17","cited_by_count":0,"area":"deeprl"},{"id":"2507.15174","title":"Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control","created":"2025-07-21","cited_by_count":0,"area":null}],"next_cursor":"100"}