SUMO

SUMO is a traffic simulation benchmark that contains scenarios for evaluating traffic signal control strategies, focusing on metrics such as queue percentiles and delay trends.

Papers using SUMO (16)

DreamerV3 for Traffic Signal Control: Hyperparameter Tuning and Performance2025 · 1 citesPedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles2026Momentum Based Reward Design for Low Emission Traffic Signal Control2026SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skills2026PALCAS: A Priority-Aware Intelligent Lane Change Advisory System for Autonomous Vehicles using Federated Reinforcement Learning2026VissimRL: A Multi-Agent Reinforcement Learning Framework for Traffic Signal Control Based on Vissim2026Dynamic Configuration of On-Street Parking Spaces using Multi Agent Reinforcement Learning2025Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations2025Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control2025Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey2025Connectivity Management in Satellite-Aided Vehicular Networks with Multi-Head Attention-Based State Estimation2025The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning2025Large-scale Regional Traffic Signal Control Based on Single-Agent Reinforcement Learning2025PyTSC: A Unified Platform for Multi-Agent Reinforcement Learning in Traffic Signal Control2024Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning2024Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization2024