# SelectLight: Learning to Select Signal Plans Generated by Distributed Model Predictive Control for Urban Traffic Networks

arXiv: https://arxiv.org/abs/2608.12256 · HTML: https://mlsanity.com/paper/2608.12256/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multi-agent reinforcement learning, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 68 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [Multi-agent reinforcement learning](https://mlsanity.com/deeprl/multi-agent-reinforcement-learning/)

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control](https://mlsanity.com/paper/1903.04527/) (2019)
- [CoLight: Learning Network-level Cooperation for Traffic Signal Control](https://mlsanity.com/paper/1905.05717/) (2019)
- [Learning values across many orders of magnitude](https://mlsanity.com/paper/1602.07714/) (2016)
- [Data-driven Economic NMPC using Reinforcement Learning](https://mlsanity.com/paper/1904.04152/) (2019)
- [MPC-Net: A First Principles Guided Policy Search](https://mlsanity.com/paper/1909.05197/) (2019)
- [Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification](https://mlsanity.com/paper/2502.02133/) (2025)
- [A Safe Reinforcement Learning driven Weights-varying Model Predictive Control for Autonomous Vehicle Motion Control](https://mlsanity.com/paper/2402.02624/) (2024)
- [Adaptive Stochastic Nonlinear Model Predictive Control with Look-ahead Deep Reinforcement Learning for Autonomous Vehicle Motion Control](https://mlsanity.com/paper/2311.04303/) (2023)
- [A Critical Review of Traffic Signal Control and A Novel Unified View of Reinforcement Learning and Model Predictive Control Approaches for Adaptive Traffic Signal Control](https://mlsanity.com/paper/2211.14426/) (2022)
- [CV-MP: Max-Pressure Control in Heterogeneously Distributed and Partially Connected Vehicle Environments](https://mlsanity.com/paper/2505.05258/) (2025)
- [Connected Vehicle Data-driven Robust Optimization for Traffic Signal Timing: Modeling Traffic Flow Variability and Errors](https://mlsanity.com/paper/2406.14108/) (2024)
- [A Probabilistic Approach for Queue Length Estimation Using License Plate Recognition Data: Considering Overtaking in Multi-lane Scenarios](https://mlsanity.com/paper/2408.06351/) (2024)

## Abstract (arXiv)

Coordinated traffic signal control across urban networks must adapt to changing demand while satisfying operational constraints. Multi-objective distributed model predictive control (DMPC) can construct feasible signal plans online, but prescribed rules for selecting among trade-off solutions cannot learn from realized closed-loop outcomes. We propose SelectLight, which implements post-optimization selection by allowing a multi-agent reinforcement learning (MARL) policy to choose directly from plans generated online by DMPC. At each control update, state-pruned multi-objective dynamic programming (SP-MODP) evaluates plans with a Newellian point--spatial queue model and returns a bounded set of mutually nondominated candidate signal plans for total queueing delay, peak queue accumulation, and total number of stops. A topology-aware attention policy trained with independent proximal policy optimization (IPPO) selects one unmodified plan from each variable-size set. This confines learning to candidate selection, preserves the prescribed signal timing constraints, and leaves the selected plan and its predicted objective trade-offs available for inspection. Experiments on two 28-intersection SUMO networks show that SelectLight achieves the best delay-related performance and that its advantage widens with demand. At twice the baseline demand, it reduces queueing delay and waiting time by 5.57% and 6.44%, respectively, relative to the strongest baseline. SelectLight also incurs the lowest transfer loss under every tested demand shift. With a 120 s prediction horizon, the per-intersection 99th-percentile SP-MODP solution time is 5.408 ms, well below the 5 s control interval.