Skip to content
AI News HubLIVE
Original source2 min read

Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control

Summary

Sim2Signal decomposes the sim-to-real gap in RL-based traffic signal control into observation, action, transition, and reward gaps matched to the four MDP components, inducing each in isolation under a shared protocol. It evaluates 18 mitigation methods on 2 base controllers across 33 gap settings and 10 calibrated networks from 5 real-world locations, finding that direct transfer always degrades and that degradation severity does not predict mitigation effectiveness.

SourcearXiv Machine LearningAuthor: Ferdous Al Rafi, Susrik Mukherjee, Latika Liladhar Dekate, Jennifer Yawa Lavoe, Huaiyuan Yao, Shlok Mohanty, Longchao Da, Xuesong Zhou, Hua Wei
Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Sep 2026]

Title:Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control

View a PDF of the paper titled Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control, by Ferdous Al Rafi and 8 other authors

View PDF HTML (experimental)

Abstract:Reinforcement learning achieves strong traffic signal control performance in simulation, yet policies trained in simulators often fail once deployed in the real world, a failure known as the Sim-to-Real gap. When RL is applied to traffic signal control, this gap arises from several sources: sensing, action execution, traffic dynamics, and the control objective. Their relative impact and the reliability of existing Sim-to-Real mitigation methods remain insufficiently understood, and the field lacks a standard benchmark for systematically measuring the gap and evaluating mitigation methods. We present Sim2Signal, a benchmark that decomposes the Sim-to-Real gap into observation, action, transition, and reward gaps, corresponding to mismatches in the four components of the underlying MDP, and induces each gap in isolation under a shared protocol. We evaluate 18 mitigation methods on 2 base controllers, across 33 gap settings and 10 calibrated networks built from 5 real-world locations. We find that direct transfer consistently degrades performance across all four gap sources, but the severity of the degradation does not predict the effectiveness of mitigation. Instead, mitigation effectiveness depends strongly on the network and gap setting: outside the action gap, a method that helps in one case may fail in another. The most effective methods generally estimate what the gap changes, rather than make the policy insensitive through domain randomization or invariant representations. Our code is available at this https URL

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2609.01676 [cs.LG]

(or arXiv:2609.01676v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.01676

arXiv-issued DOI via DataCite

Submission history

From: Ferdous Al Rafi [view email] [v1] Tue, 1 Sep 2026 08:15:22 UTC (5,961 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control, by Ferdous Al Rafi and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Decomposes the sim-to-real gap into observation, action, transition, and reward gaps and induces each in isolation under a shared protocol.
  • Benchmarks 18 mitigation methods, 2 base controllers, 33 gap settings, and 10 calibrated networks built from 5 real-world locations.
  • Outside the action gap, mitigation effectiveness depends strongly on the network and gap setting, so a method that helps in one case may fail in another.
  • The most effective methods estimate what the gap changes rather than relying on domain randomization or invariant representations to make the policy insensitive.

Highlights and analysis are generated automatically and may contain errors. Check the original source.