{"total":52,"rows":[{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2506.21976","title":"SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model","created":"2025-06-27","cited_by_count":20,"area":"wm"},{"id":"2211.10871","title":"SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control","created":"2022-11-20","cited_by_count":15,"area":null},{"id":"2312.05090","title":"UniTSA: A Universal Reinforcement Learning Framework for V2X Traffic Signal Control","created":"2023-12-08","cited_by_count":13,"area":null},{"id":"2404.12090","title":"X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner","created":"2024-04-18","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":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2201.13143","title":"CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learning","created":"2022-01-31","cited_by_count":6,"area":"driving"},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"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":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2109.14337","title":"Deep Reinforcement Q-Learning for Intelligent Traffic Signal Control with Partial Detection","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2301.00637","title":"Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach","created":"2023-01-02","cited_by_count":4,"area":null},{"id":"2310.16772","title":"AI Agent as Urban Planner: Steering Stakeholder Dynamics in Urban Planning via Consensus-based Multi-Agent Reinforcement Learning","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2106.12194","title":"Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving","created":"2021-06-23","cited_by_count":3,"area":"driving"},{"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":"2210.13378","title":"ADLight: A Universal Approach of Traffic Signal Control with Augmented Data Using Reinforcement Learning","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2302.03669","title":"Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systems","created":"2023-02-04","cited_by_count":3,"area":null},{"id":"2503.01632","title":"CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution","created":"2025-03-03","cited_by_count":3,"area":"lr"},{"id":"2505.19486","title":"VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture","created":"2025-05-26","cited_by_count":3,"area":"lr"},{"id":"2205.01278","title":"Real-time Cooperative Vehicle Coordination at Unsignalized Road Intersections","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2501.15820","title":"FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2603.24366","title":"CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control","created":"2026-03-25","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":"2112.13817","title":"Intelligent Traffic Light via Policy-based Deep Reinforcement Learning","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2210.06399","title":"DQLAP: Deep Q-Learning Recommender Algorithm with Update Policy for a Real Steam Turbine System","created":"2022-10-12","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":"2312.13910","title":"Multi-Agent Probabilistic Ensembles with Trajectory Sampling for Connected Autonomous Vehicles","created":"2023-12-21","cited_by_count":1,"area":"driving"},{"id":"2407.10811","title":"GuideLight: \"Industrial Solution\" Guidance for More Practical Traffic Signal Control Agents","created":"2024-07-15","cited_by_count":1,"area":"deeprl"},{"id":"2503.02315","title":"Incorporating graph neural network into route choice model","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2608.20858","title":"Sharing the Control Authority Between Deep Reinforcement Learning and Model Predictive Control: Application to Multi-Class Transportation Networks","created":"2026-08-21","cited_by_count":1,"area":"deeprl"},{"id":"2608.27010","title":"A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2107.02361","title":"Effects of Smart Traffic Signal Control on Air Quality","created":"2021-07-06","cited_by_count":0,"area":null},{"id":"2107.14374","title":"Modelling and Reasoning Techniques for Context Aware Computing in Intelligent Transportation System","created":"2021-07-29","cited_by_count":0,"area":null},{"id":"2204.03061","title":"Standardized feature extraction from pairwise conflicts applied to the train rescheduling problem","created":"2022-04-06","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":"2211.16687","title":"Automatic Discovery of Multi-perspective Process Model using Reinforcement Learning","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2310.10856","title":"Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2310.10948","title":"Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2311.13905","title":"A DRL solution to help reduce the cost in waiting time of securing a traffic light for cyclists","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2407.17303","title":"MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning","created":"2024-07-24","cited_by_count":0,"area":"deeprl"},{"id":"2408.00814","title":"Adaptive traffic signal safety and efficiency improvement by multi objective deep reinforcement learning approach","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2503.14250","title":"A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control","created":"2025-03-18","cited_by_count":0,"area":"deeprl"},{"id":"2503.20462","title":"Multi-agent Uncertainty-Aware Pessimistic Model-Based Reinforcement Learning for Connected Autonomous Vehicles","created":"2025-03-26","cited_by_count":0,"area":"driving"},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2512.04653","title":"A Semi Centralized Training Decentralized Execution Architecture for Multi Agent Deep Reinforcement Learning in Traffic Signal Control","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.09368","title":"CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning","created":"2025-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2605.10170","title":"Balancing Efficiency and Fairness in Traffic Light Control through Deep Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.29693","title":"Momentum Based Reward Design for Low Emission Traffic Signal Control","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.03703","title":"Explainable Reinforcement Learning for Adaptive Traffic Signal Control","created":"2026-07-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.15930","title":"Multi-Horizon Explainable Queue Forecasting and Resource-Aware Decision Support for Intelligent Border Control Using LightGBM","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}