{"total":73,"rows":[{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2502.14743","title":"Multi-Agent Coordination across Diverse Applications: A Survey","created":"2025-02-20","cited_by_count":37,"area":"agents"},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32,"area":"driving"},{"id":"2210.04688","title":"BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets","created":"2022-10-07","cited_by_count":25,"area":"offlinerl"},{"id":"2410.14368","title":"CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic","created":"2024-10-18","cited_by_count":22,"area":"agents"},{"id":"2306.08094","title":"Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2302.00171","title":"Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach","created":"2023-02-01","cited_by_count":15,"area":null},{"id":"2404.02429","title":"AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Dataset","created":"2024-04-03","cited_by_count":15,"area":"driving"},{"id":"2208.00268","title":"Unified Automatic Control of Vehicular Systems with Reinforcement Learning","created":"2022-07-30","cited_by_count":13,"area":null},{"id":"2301.05294","title":"Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2302.09167","title":"Mixed Traffic Control and Coordination from Pixels","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2204.12561","title":"Learning Eco-Driving Strategies at Signalized Intersections","created":"2022-04-26","cited_by_count":9,"area":"driving"},{"id":"2311.12261","title":"EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learning","created":"2023-11-21","cited_by_count":9,"area":null},{"id":"2404.00796","title":"CARL: Congestion-Aware Reinforcement Learning for Imitation-based Perturbations in Mixed Traffic Control","created":"2024-03-31","cited_by_count":7,"area":"deeprl"},{"id":"2408.17380","title":"Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control","created":"2024-08-30","cited_by_count":7,"area":"deeprl"},{"id":"2410.15221","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","created":"2024-10-19","cited_by_count":7,"area":"driving"},{"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":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2312.09436","title":"Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2404.06229","title":"Autonomous Driving Small-Scale Cars: A Survey of Recent Development","created":"2024-04-09","cited_by_count":6,"area":null},{"id":"2108.00138","title":"Learning to Control DC Motor for Micromobility in Real Time with Reinforcement Learning","created":"2021-07-31","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":"2403.04232","title":"Generalizing Cooperative Eco-driving via Multi-residual Task Learning","created":"2024-03-07","cited_by_count":5,"area":"driving"},{"id":"2507.14850","title":"Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2112.03759","title":"Learning a Robust Multiagent Driving Policy for Traffic Congestion Reduction","created":"2021-12-03","cited_by_count":4,"area":"driving"},{"id":"2112.07569","title":"Cooperation for Scalable Supervision of Autonomy in Mixed Traffic","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2308.00864","title":"PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems","created":"2023-08-01","cited_by_count":4,"area":null},{"id":"2302.09140","title":"Towards Co-operative Congestion Mitigation","created":"2023-02-17","cited_by_count":3,"area":null},{"id":"2402.00334","title":"Multi-agent Path Finding for Cooperative Autonomous Driving","created":"2024-02-01","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":"2309.08254","title":"Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2309.15252","title":"V2X-Lead: LiDAR-based End-to-End Autonomous Driving with Vehicle-to-Everything Communication Integration","created":"2023-09-26","cited_by_count":2,"area":"driving"},{"id":"2312.10339","title":"Model-free Learning of Corridor Clearance: A Near-term Deployment Perspective","created":"2023-12-16","cited_by_count":2,"area":null},{"id":"2408.05609","title":"Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at Scale","created":"2024-08-10","cited_by_count":2,"area":"driving"},{"id":"2409.13783","title":"A Value Based Parallel Update MCTS Method for Multi-Agent Cooperative Decision Making of Connected and Automated Vehicles","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2504.04691","title":"Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2506.17213","title":"Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2209.15626","title":"B2RL: An open-source Dataset for Building Batch Reinforcement Learning","created":"2022-09-30","cited_by_count":1,"area":"offlinerl"},{"id":"2211.05297","title":"Coordinating CAV Swarms at Intersections with a Deep Learning Model","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2310.03303","title":"A Two-stage Based Social Preference Recognition in Multi-Agent Autonomous Driving System","created":"2023-10-05","cited_by_count":1,"area":"driving"},{"id":"2402.17050","title":"Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test","created":"2024-02-26","cited_by_count":1,"area":"deeprl"},{"id":"2403.11914","title":"Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Driving","created":"2024-03-18","cited_by_count":1,"area":"driving"},{"id":"2403.14879","title":"Learning to Change: Choreographing Mixed Traffic Through Lateral Control and Hierarchical Reinforcement Learning","created":"2024-03-21","cited_by_count":1,"area":"deeprl"},{"id":"2405.08655","title":"A Distributed Approach to Autonomous Intersection Management via Multi-Agent Reinforcement Learning","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2407.00553","title":"Cooperative Advisory Residual Policies for Congestion Mitigation","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2409.03881","title":"Multi-agent Path Finding for Mixed Autonomy Traffic Coordination","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2412.09782","title":"EI-Drive: A Platform for Cooperative Perception with Realistic Communication Models","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2507.09836","title":"Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systems","created":"2025-07-14","cited_by_count":1,"area":"moe"},{"id":"2507.12110","title":"Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2601.06776","title":"From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design","created":"2026-01-11","cited_by_count":1,"area":"agents"},{"id":"2303.13992","title":"Physical Backdoor Trigger Activation of Autonomous Vehicle using Reachability Analysis","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2304.12821","title":"Zero-shot Transfer Learning of Driving Policy via Socially Adversarial Traffic Flow","created":"2023-04-25","cited_by_count":0,"area":"driving"},{"id":"2305.09600","title":"Deep Reinforcement Learning to Maximize Arterial Usage during Extreme Congestion","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2311.11866","title":"Analyzing Emissions and Energy Efficiency at Unsignalized Real-world Intersections Under Mixed Traffic Control","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2407.13775","title":"Lessons in Cooperation: A Qualitative Analysis of Driver Sentiments towards Real-Time Advisory Systems from a Driving Simulator User Study","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2408.07578","title":"A Nested Graph Reinforcement Learning-based Decision-making Strategy for Eco-platooning","created":"2024-08-14","cited_by_count":0,"area":"deeprl"},{"id":"2501.16728","title":"Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark","created":"2025-01-28","cited_by_count":0,"area":"deeprl"},{"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":"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":"2507.09311","title":"A Fairness-Oriented Multi-Objective Reinforcement Learning approach for Autonomous Intersection Management","created":"2025-07-12","cited_by_count":0,"area":"deeprl"},{"id":"2508.07453","title":"Noise-Aware Generative Microscopic Traffic Simulation","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2509.01611","title":"A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle","created":"2025-09-01","cited_by_count":0,"area":"driving"},{"id":"2601.14429","title":"Measuring the State of Open Science in Transportation Using Large Language Models","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.21852","title":"LightSim: A Lightweight Cell Transmission Model Simulator for Traffic Signal Control Research","created":"2026-02-25","cited_by_count":0,"area":"deeprl"},{"id":"2604.12857","title":"Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic","created":"2026-04-14","cited_by_count":0,"area":null},{"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":"2605.30719","title":"When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.01639","title":"Autonomous discovery of traffic laws with AI traffic scientists","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.06467","title":"Local and Global Stability in Performative Reinforcement Learning","created":"2026-09-06","cited_by_count":0,"area":"deeprl"},{"id":"2609.15544","title":"Specifying Reward Functions for RL Without Environment Sampling","created":"2026-09-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}