mlsanityData to 14 Oct 2026

Flow: A Modular Learning Framework for Mixed Autonomy Traffic

arXiv 1710.05465 ↗First posted 16 Oct 2017cs.AI cs.RO cs.SYcited by 73

Not on the map. Why?

Abstract (arXiv)

The rapid development of autonomous vehicles (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility. However, the progression of these impacts, as AVs are adopted, is not well understood. Numerous technical challenges arise from the goal of analyzing the partial adoption of autonomy: partial control and observation, multi-vehicle interactions, and the sheer variety of scenarios represented by real-world networks. To shed light into near-term AV impacts, this article studies the suitability of deep reinforcement learning (RL) for overcoming these challenges in a low AV-adoption regime. A modular learning framework is presented, which leverages deep RL to address complex traffic dynamics. Modules are composed to capture common traffic phenomena (stop-and-go traffic jams, lane changing, intersections). Learned control laws are found to improve upon human driving performance, in terms of system-level velocity, by up to 57% with only 4-7% adoption of AVs. Furthermore, in single-lane traffic, a small neural network control law with only local observation is found to eliminate stop-and-go traffic - surpassing all known model-based controllers to achieve near-optimal performance - and generalize to out-of-distribution traffic densities.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 16; 2024: 21; 2025: 14; 2026: 9.

73 papers.

Sort:

By area:

  1. 2022The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Modelscited by 328
  2. 2024Correlated Proxies: A New Definition and Improved Mitigation for Reward Hackingcited by 50
  3. 2025Multi-Agent Coordination across Diverse Applications: A Surveycited by 37
  4. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 32
  5. 2022BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasetscited by 25
  6. 2024CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Trafficcited by 22
  7. 2023Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learningcited by 20
  8. 2022Reward Reports for Reinforcement Learningcited by 18
  9. 2023Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approachcited by 15
  10. 2024AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Datasetcited by 15
  11. 2022Unified Automatic Control of Vehicular Systems with Reinforcement Learningcited by 13
  12. 2023Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersectionscited by 12
38 more
  1. 2023Mixed Traffic Control and Coordination from Pixelscited by 10
  2. 2022Learning Eco-Driving Strategies at Signalized Intersectionscited by 9
  3. 2023EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learningcited by 9
  4. 2024CARL: Congestion-Aware Reinforcement Learning for Imitation-based Perturbations in Mixed Traffic Controlcited by 7
  5. 2024Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory controlcited by 7
  6. 2024IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learningcited by 7
  7. 2022CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learningcited by 6
  8. 2022Reinforcement Learning in Practice: Opportunities and Challengescited by 6
  9. 2023Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomycited by 6
  10. 2024Autonomous Driving Small-Scale Cars: A Survey of Recent Developmentcited by 6
  11. 2021Learning to Control DC Motor for Micromobility in Real Time with Reinforcement Learningcited by 5
  12. 2022Offline Reinforcement Learning for Road Traffic Controlcited by 5
  13. 2024Generalizing Cooperative Eco-driving via Multi-residual Task Learningcited by 5
  14. 2025Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systemscited by 5
  15. 2021Learning a Robust Multiagent Driving Policy for Traffic Congestion Reductioncited by 4
  16. 2021Cooperation for Scalable Supervision of Autonomy in Mixed Trafficcited by 4
  17. 2023PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systemscited by 4
  18. 2023Towards Co-operative Congestion Mitigationcited by 3
  19. 2024Multi-agent Path Finding for Cooperative Autonomous Drivingcited by 3
  20. 2025TranSimHub:A Unified Air-Ground Simulation Platform for Multi-Modal Perception and Decision-Makingcited by 3
  21. 2023Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluationcited by 2
  22. 2023V2X-Lead: LiDAR-based End-to-End Autonomous Driving with Vehicle-to-Everything Communication Integrationcited by 2
  23. 2023Model-free Learning of Corridor Clearance: A Near-term Deployment Perspectivecited by 2
  24. 2024Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at Scalecited by 2
  25. 2024A Value Based Parallel Update MCTS Method for Multi-Agent Cooperative Decision Making of Connected and Automated Vehiclescited by 2
  26. 2025Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learningcited by 2
  27. 2025Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generationcited by 2
  28. 2022B2RL: An open-source Dataset for Building Batch Reinforcement Learningcited by 1
  29. 2022Coordinating CAV Swarms at Intersections with a Deep Learning Modelcited by 1
  30. 2023A Two-stage Based Social Preference Recognition in Multi-Agent Autonomous Driving Systemcited by 1
  31. 2024Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational testcited by 1
  32. 2024Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Drivingcited by 1
  33. 2024Learning to Change: Choreographing Mixed Traffic Through Lateral Control and Hierarchical Reinforcement Learningcited by 1
  34. 2024A Distributed Approach to Autonomous Intersection Management via Multi-Agent Reinforcement Learningcited by 1
  35. 2024Cooperative Advisory Residual Policies for Congestion Mitigationcited by 1
  36. 2024Multi-agent Path Finding for Mixed Autonomy Traffic Coordinationcited by 1
  37. 2024EI-Drive: A Platform for Cooperative Perception with Realistic Communication Modelscited by 1
  38. 2025Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systemscited by 1

50 most cited of 73 All 73 (JSON)