# Learning an Interpretable Traffic Signal Control Policy

arXiv: https://arxiv.org/abs/1912.11023 · HTML: https://mlsanity.com/paper/1912.11023/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2019.

## Built on by (most cited first, 20 of 20)

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control](https://mlsanity.com/paper/2211.10871/) (2022)
- [Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method](https://mlsanity.com/paper/2204.12190/) (2022)
- [The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning](https://mlsanity.com/paper/2210.08607/) (2022)
- [The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality](https://mlsanity.com/paper/2206.11996/) (2022)
- [DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledge](https://mlsanity.com/paper/2312.14532/) (2023)
- [Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges](https://mlsanity.com/paper/2211.14732/) (2022)
- [Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach](https://mlsanity.com/paper/2312.07795/) (2023)
- [Task Phasing: Automated Curriculum Learning from Demonstrations](https://mlsanity.com/paper/2210.10999/) (2022)
- [SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control](https://mlsanity.com/paper/2511.05790/) (2025)
- [Real-Time Network-Level Traffic Signal Control: An Explicit Multiagent Coordination Method](https://mlsanity.com/paper/2306.08843/) (2023)
- [Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning](https://mlsanity.com/paper/2412.03925/) (2024)
- [A Methodology for the Development of RL-Based Adaptive Traffic Signal Controllers](https://mlsanity.com/paper/2101.09614/) (2021)
- [Cooperative Multi-Objective Reinforcement Learning for Traffic Signal Control and Carbon Emission Reduction](https://mlsanity.com/paper/2306.09662/) (2023)
- [Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control](https://mlsanity.com/paper/2506.12453/) (2025)
- [Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Study](https://mlsanity.com/paper/2506.13836/) (2025)
- [HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control](https://mlsanity.com/paper/2506.14391/) (2025)
- [A Semi Centralized Training Decentralized Execution Architecture for Multi Agent Deep Reinforcement Learning in Traffic Signal Control](https://mlsanity.com/paper/2512.04653/) (2025)
- [UCATSC: Uncertainty-Aware Constrained Traffic Signal Control Under Vision-Based Partial Observability](https://mlsanity.com/paper/2602.07784/) (2026)
- [Momentum Based Reward Design for Low Emission Traffic Signal Control](https://mlsanity.com/paper/2605.29693/) (2026)

## Abstract (arXiv)

Signalized intersections are managed by controllers that assign right of way (green, yellow, and red lights) to non-conflicting directions. Optimizing the actuation policy of such controllers is expected to alleviate traffic congestion and its adverse impact. Given such a safety-critical domain, the affiliated actuation policy is required to be interpretable in a way that can be understood and regulated by a human. This paper presents and analyzes several on-line optimization techniques for tuning interpretable control functions. Although these techniques are defined in a general way, this paper assumes a specific class of interpretable control functions (polynomial functions) for analysis purposes. We show that such an interpretable policy function can be as effective as a deep neural network for approximating an optimized signal actuation policy. We present empirical evidence that supports the use of value-based reinforcement learning for on-line training of the control function. Specifically, we present and study three variants of the Deep Q-learning algorithm that allow the training of an interpretable policy function. Our Deep Regulatable Hardmax Q-learning variant is shown to be particularly effective in optimizing our interpretable actuation policy, resulting in up to 19.4% reduced vehicles delay compared to commonly deployed actuated signal controllers.