mlsanityData to 14 Oct 2026

URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles

arXiv 2505.17734 ↗First posted 23 May 2025cs.LGcited by 4

On the map: End-to-end autonomous driving → Cooperative and V2X driving

Abstract (arXiv)

Connected Autonomous Vehicles (CAVs) promise to reduce congestion in future urban networks, potentially by optimizing their routing decisions. Unlike for human drivers, these decisions can be made with collective, data-driven policies, developed using machine learning algorithms. Reinforcement learning (RL) can facilitate the development of such collective routing strategies, yet standardized and realistic benchmarks are missing. To that end, we present URB: Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles. URB is a comprehensive benchmarking environment that unifies evaluation across 29 real-world traffic networks paired with realistic demand patterns. URB comes with a catalog of predefined tasks, multi-agent RL (MARL) algorithm implementations, three baseline methods, domain-specific performance metrics, and a modular configuration scheme. Our results show that, despite the lengthy and costly training, state-of-the-art MARL algorithms rarely outperformed humans. The experimental results reported in this paper initiate the first leaderboard for MARL in large-scale urban routing optimization. They reveal that current approaches struggle to scale, emphasizing the urgent need for advancements in this domain.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Cooperative and V2X driving, one of 9 directions in End-to-end autonomous driving. Builds on 25 of its 68 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

25 of 68 references.

References · 25

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  3. 2017Deep Reinforcement Learning that Matterscited by 754
  4. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  5. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  6. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 294
  7. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  8. 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 236
  9. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  10. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  11. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  12. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
13 more
  1. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
  2. 2017Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learningcited by 117
  3. 2023TorchRL: A data-driven decision-making library for PyTorchcited by 60
  4. 2024An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learningcited by 50
  5. 2023BenchMARL: Benchmarking Multi-Agent Reinforcement Learningcited by 33
  6. 2021Regularized Softmax Deep Multi-Agent Q-Learningcited by 19
  7. 2023Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?cited by 18
  8. 2023Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learningcited by 13
  9. 2020InTAS -- The Ingolstadt Traffic Scenario for SUMOcited by 11
  10. 2020Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learningcited by 10
  11. 2020Multi-Agent Reinforcement Learning for Markov Routing Games: A New Modeling Paradigm For Dynamic Traffic Assignmentcited by 9
  12. 2021Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environmentscited by 5
  13. 2025RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehiclescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Autonomous vehicles need social awareness to find optima in multi-agent reinforcement learning routing gamescited by 1
  2. 2026Generalising Travel Time Prediction To Varying Route Choices In Urban Networkscited by 0
  3. 2026PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillationcited by 0
  4. 2026Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Driverscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing
  2. 2025Impact of Collective Behaviors of Autonomous Vehicles on Urban Traffic Dynamics: A Multi-Agent Reinforcement Learning Approach
  3. 2026Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs
  4. 2025Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement Learning
  5. 2025Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
  6. 2025Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark
  7. 2021Scalable Multiagent Driving Policies For Reducing Traffic Congestion
  8. 2024Neighbor-Aware Reinforcement Learning for Mixed Traffic Optimization in Large-scale Networks