mlsanityData to 14 Oct 2026

A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control

arXiv 2503.14250 ↗First posted 18 Mar 2025cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

Adaptive traffic signal control (ATSC) can effectively reduce vehicle travel times by dynamically adjusting signal timings but poses a critical challenge in real-world scenarios due to the complexity of real-time decision-making in dynamic and uncertain traffic conditions. The burgeoning field of intelligent transportation systems, bolstered by artificial intelligence techniques and extensive data availability, offers new prospects for the implementation of ATSC. In this study, we introduce a parallel hybrid action space reinforcement learning model (PH-DDPG) that optimizes traffic signal phase and duration of traffic signals simultaneously, eliminating the need for sequential decision-making seen in traditional two-stage models. Our model features a task-specific parallel hybrid action space tailored for adaptive traffic control, which directly outputs discrete phase selections and their associated continuous duration parameters concurrently, thereby inherently addressing dynamic traffic adaptation through unified parametric optimization. %Our model features a unique parallel hybrid action space that allows for the simultaneous output of each action and its optimal parameters, streamlining the decision-making process. Furthermore, to ascertain the robustness and effectiveness of this approach, we executed ablation studies focusing on the utilization of a random action parameter mask within the critic network, which decouples the parameter space for individual actions, facilitating the use of preferable parameters for each action. The results from these studies confirm the efficacy of this method, distinctly enhancing real-world applicability

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 13 of its 29 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

13 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024CycLight: learning traffic signal cooperation with a cycle-level strategy16 Jan

Other references · 12

  1. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  2. 2019Learning Phase Competition for Traffic Signal Controlcited by 87
  3. 2015Reinforcement Learning with Parameterized Actionscited by 63
  4. 2020AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Controlcited by 62
  5. 2018Deep Reinforcement Learning for Traffic Light Control in Vehicular Networkscited by 52
  6. 2017Deep Deterministic Policy Gradient for Urban Traffic Light Controlcited by 30
  7. 2021Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlcited by 29
  8. 2019Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spacescited by 24
  9. 2021Efficient Pressure: Improving efficiency for signalized intersectionscited by 24
  10. 2023DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledgecited by 9
  11. 2023DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedbackcited by 7
  12. 2022Reinforcement learning for traffic signal control in hybrid action spacecited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control
  2. 2025Reinforcement Learning Based Traffic Signal Design to Minimize Queue Lengths
  3. 2024Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion
  4. 2025Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control
  5. 2026Evaluating the Robustness of Reinforcement Learning based Adaptive Traffic Signal Control
  6. 2026A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control
  7. 2023A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning
  8. 2025Toward Dependency Dynamics in Multi-Agent Reinforcement Learning for Traffic Signal Control