# DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning

arXiv: https://arxiv.org/abs/2605.21311 · HTML: https://mlsanity.com/paper/2605.21311/

## 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 21 of its 50 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2005.08514/) (2020)
- [TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors](https://mlsanity.com/paper/2101.06557/) (2021)
- [CoLight: Learning Network-level Cooperation for Traffic Signal Control](https://mlsanity.com/paper/1905.05717/) (2019)
- [CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario](https://mlsanity.com/paper/1905.05217/) (2019)
- [CityDreamer: Compositional Generative Model of Unbounded 3D Cities](https://mlsanity.com/paper/2309.00610/) (2023)
- [AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control](https://mlsanity.com/paper/2010.05772/) (2020)
- [Graph Neural Networks for Modelling Traffic Participant Interaction](https://mlsanity.com/paper/1903.01254/) (2019)
- [Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models](https://mlsanity.com/paper/2412.05334/) (2024)
- [SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries](https://mlsanity.com/paper/2401.00391/) (2023)
- [Causal Composition Diffusion Model for Closed-loop Traffic Generation](https://mlsanity.com/paper/2412.17920/) (2024)
- [SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model](https://mlsanity.com/paper/2506.21976/) (2025)
- [WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2407.15350/) (2024)
- [COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation](https://mlsanity.com/paper/2407.11294/) (2024)
- [LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation](https://mlsanity.com/paper/2403.17601/) (2024)
- [Road Planning for Slums via Deep Reinforcement Learning](https://mlsanity.com/paper/2305.13060/) (2023)
- [Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement Learning](https://mlsanity.com/paper/2504.05018/) (2025)
- [Adaptive Road Configurations for Improved Autonomous Vehicle-Pedestrian Interactions using Reinforcement Learning](https://mlsanity.com/paper/2303.12289/) (2023)

## Abstract (arXiv)

Modern vision systems can detect, track, and forecast urban actors at scale, yet translating perception outputs to urban design remains limited. We introduce DeCoR, a two-stage reinforcement learning framework that leverages flow observations to co-optimize crosswalk layout and network-level signal control. The design stage encodes the pedestrian network as a graph and learns a generative policy that parameterizes a Gaussian mixture model over crosswalk location and width, from which new crosswalks are sampled. For each layout, a shared control policy learns adaptive signal timings to minimize joint pedestrian and vehicle delay. On a 750 m real-world urban corridor with demand sensed from video and Wi-Fi logs, DeCoR learns a layout that reduces pedestrian arrival time to their nearest crosswalk by 23% while using fewer crosswalks than existing configurations. On the control side, DeCoR reduces pedestrian and vehicle wait time by 79% and 65%, respectively, relative to fixed-time signalization. Further, the control policy generalizes to demands outside of training and is robust to layout changes without retraining.