mlsanityData to 14 Oct 2026

SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control

arXiv 2511.05790 ↗First posted 8 Nov 2025cs.LG cs.AIcited by 2

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

Abstract (arXiv)

Deep Reinforcement Learning have achieved significant success in automatically devising effective traffic signal control (TSC) policies. Neural policies, however, tend to be over-parameterized and non-transparent, hindering their interpretability and deployability on resource-limited edge devices. This work presents SymLight, a priority function search framework based on Monte Carlo Tree Search (MCTS) for discovering inherently interpretable and deployable symbolic priority functions to serve as the TSC policies. The priority function, in particular, accepts traffic features as input and then outputs a priority for each traffic signal phase, which subsequently directs the phase transition. For effective search, we propose a concise yet expressive priority function representation. This helps mitigate the combinatorial explosion of the action space in MCTS. Additionally, a probabilistic structural rollout strategy is introduced to leverage structural patterns from previously discovered high-quality priority functions, guiding the rollout process. Our experiments on real-world datasets demonstrate SymLight's superior performance across a range of baselines. A key advantage is SymLight's ability to produce interpretable and deployable TSC policies while maintaining excellent performance.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 36 references that are in the map. First posted on arXiv 8 Nov 2025.

Builds on

17 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Generalized Phase Pressure Control Enhanced Reinforcement Learning for Traffic Signal Control26 Mar

Other references · 16

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2019Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradientscited by 309
  4. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  5. 2019Learning Phase Competition for Traffic Signal Controlcited by 87
  6. 2023LLMLight: Large Language Models as Traffic Signal Control Agentscited by 73
  7. 2022Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree searchcited by 66
  8. 2019Diagnosing Reinforcement Learning for Traffic Signal Controlcited by 33
  9. 2024LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environmentscited by 31
  10. 2021Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlcited by 29
  11. 2019Learning an Interpretable Traffic Signal Control Policycited by 20
  12. 2025Uncertainty Quantification of Large Language Models through Multi-Dimensional Responsescited by 18
4 more
  1. 2018Position weighted backpressure intersection control for urban networkscited by 5
  2. 2022TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resourcescited by 3
  3. 2024Learning Traffic Signal Control via Genetic Programmingcited by 3
  4. 2025GPLight+: A Genetic Programming Method for Learning Symmetric Traffic Signal Control Policycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skillscited by 1
  2. 2026Active Inference for Adaptive Traffic Signal Control in Noisy Nonstationary IoT Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evolutionary Discovery of Heuristic Policies for Traffic Signal Control
  2. 2024MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control
  3. 2025A Hierarchical Deep Reinforcement Learning Framework for Traffic Signal Control with Predictable Cycle Planning
  4. 2026ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Control
  5. 2024Optimizing Traffic Signal Control using High-Dimensional State Representation and Efficient Deep Reinforcement Learning
  6. 2023A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning
  7. 2026Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control
  8. 2026EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs