Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark
On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic
Abstract (arXiv)
This paper presents a mixed traffic control policy designed to optimize traffic efficiency across diverse road topologies, addressing issues of congestion prevalent in urban environments. A model-free reinforcement learning (RL) approach is developed to manage large-scale traffic flow, using data collected by autonomous vehicles to influence human-driven vehicles. A real-world mixed traffic control benchmark is also released, which includes 444 scenarios from 20 countries, representing a wide geographic distribution and covering a variety of scenarios and road topologies. This benchmark serves as a foundation for future research, providing a realistic simulation environment for the development of effective policies. Comprehensive experiments demonstrate the effectiveness and adaptability of the proposed method, achieving better performance than existing traffic control methods in both intersection and roundabout scenarios. To the best of our knowledge, this is the first project to introduce a real-world complex scenarios mixed traffic control benchmark. Videos and code of our work are available at https://sites.google.com/berkeley.edu/mixedtrafficplus/home
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 37 references that are in the map. First posted on arXiv 28 Jan 2025.
Builds on
14 of 37 references.
References · 14
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
- 2019A Survey on Traffic Signal Control Methodscited by 79
- 2017Flow: A Modular Learning Framework for Mixed Autonomy Trafficcited by 73
- 2019SUMMIT: A Simulator for Urban Driving in Massive Mixed Trafficcited by 40
- 2019Discrete and Continuous Action Representation for Practical RL in Video Gamescited by 39
- 2018Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehiclescited by 19
- 2021Reinforcement Learning for Mixed Autonomy Intersectionscited by 16
- 2023Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersectionscited by 12
- 2023Large-scale Mixed Traffic Control Using Dynamic Vehicle Routing and Privacy-Preserving Crowdsourcingcited by 12
- 2016Polling-systems-based Autonomous Vehicle Coordination in Traffic Intersections with No Traffic Signalscited by 5
- 2020Towards a Systematic Computational Framework for Modeling Multi-Agent Decision-Making at Micro Level for Smart Vehicles in a Smart Worldcited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning
- 2024Learning to Change: Choreographing Mixed Traffic Through Lateral Control and Hierarchical Reinforcement Learning
- 2024Neighbor-Aware Reinforcement Learning for Mixed Traffic Optimization in Large-scale Networks
- 2024Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion
- 2025Self-Regulating Cars: Automating Traffic Control in Free Flow Road Networks
- 2021Scalable Multiagent Driving Policies For Reducing Traffic Congestion
- 2025Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
- 2025Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement Learning