跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19951 · v1

Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers

首次提交 2026-11-15 19:47
版本更新 2026-11-15 19:47
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

Traffic signal control (TSC) is critical for mitigating urban congestion. Deep reinforcement learning (DRL) has achieved strong performance by learning adaptive policies from traffic observations, but learned neural controllers are often opaque, structurally complex, and difficult to generalize across scenarios. We propose PPL-TSC, a programmatic policy learning framework that distills compact and human-readable TSC policies from DRL teachers. PPL-TSC formulates policy learning as an evolutionary search over phase utility functions (PUFs), which score candidate signal phases and select the highest-utility phase for execution. Each generation consists of four steps: policy generation, policy review, policy calibration, and policy evaluation. In the generation step, a large language model (LLM) acts as a semantics-aware evolutionary operator to propose and refine candidate PUFs. Generated PUFs are screened through explicit checks for syntactic validity, mathematical soundness, and consistency with TSC principles, with invalid ones repaired through iterative feedback. Valid PUFs are then calibrated to improve behavioral fidelity to the DRL teacher, and evaluated using a joint score combining teacher fidelity and traffic-control performance to select candidates for the next generation. Extensive experiments across diverse traffic scenarios and representative DRL-based controllers show that PPL-TSC produces compact and human-readable policies, achieves competitive performance for most teacher families, improves transfer generalization, and substantially reduces computational cost. Code is available at https://github.com/ForrestXie9/PPL-TSC.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 19:47 · 最新观测版本

Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers

Traffic signal control (TSC) is critical for mitigating urban congestion. Deep reinforcement learning (DRL) has achieved strong performance by learning adaptive policies from traffic observations, but learned neural controllers are often opaque, structurally complex, and difficult to generalize across scenarios. We propose PPL-TSC, a programmatic policy learning framework that distills compact and human-readable TSC policies from DRL teachers. PPL-TSC formulates policy learning as an evolutionary search over phase utility functions (PUFs), which score candidate signal phases and select the highest-utility phase for execution. Each generation consists of four steps: policy generation, policy review, policy calibration, and policy evaluation. In the generation step, a large language model (LLM) acts as a semantics-aware evolutionary operator to propose and refine candidate PUFs. Generated PUFs are screened through explicit checks for syntactic validity, mathematical soundness, and consistency with TSC principles, with invalid ones repaired through iterative feedback. Valid PUFs are then calibrated to improve behavioral fidelity to the DRL teacher, and evaluated using a joint score combining teacher fidelity and traffic-control performance to select candidates for the next generation. Extensive experiments across diverse traffic scenarios and representative DRL-based controllers show that PPL-TSC produces compact and human-readable policies, achieves competitive performance for most teacher families, improves transfer generalization, and substantially reduces computational cost. Code is available at https://github.com/ForrestXie9/PPL-TSC.

查看此版本解读 →查看此版本原文 ↗