Traffic Signal Control With Multi-Agent Reinforcement Learning: A Case Study of a Mid-Sized City Deployment

Authors

  • Reijo Heikkila Centre for Machine Learning Research, Pohjois-Karjala Centre for Machine Intelligence, Joensuu, Finland Author
  • Otakar Tichanek Department of Transport Engineering, Chrudimsko Institute of Applied Artificial Intelligence, Chrudim, Czech Republic Author
  • Purificacion Aizpurua Department of Operations Research, Bages Institute of Applied Artificial Intelligence, Manresa, Spain Author

DOI:

https://doi.org/10.5281/zenodo.22660815

Keywords:

Traffic Signal Control With Multi-Agent Reinforcement Learning; Applied machine learning; Evidence synthesis; Production deployment; MLOps

Abstract

Traffic Signal Control With Multi-Agent Reinforcement Learning is an area of active development in applied machine learning,
with evidence that has accumulated unevenly across its component questions. We review the current evidence base for traffic
signal control with multi-agent reinforcement learning, spanning methodological, implementation, governance, and cost
dimensions, focusing on where practice has converged and where it continues to vary, and set out the practical considerations
relevant to a team considering its adoption. We conclude that selective, context-specific use is best supported by the evidence
currently available, rather than uniform adoption or avoidance

References

Alvez D, Dumitrescu A, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a benchmark study". J Mach Learn Res 8(2014): 80-86. DOI: 10.1007/s10916-024-02104-9

Brankovic K, Kowalczyk B, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a systematic evaluation". IEEE Trans Pattern Anal Mach Intell 10(2017): 91-98. DOI: 10.3389/fdgth.2026.1896184

Castellani R, Ristic C, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a empirical analysis". Proc NeurIPS 12(2020): 102-110. DOI: 10.3390/diagnostics15162117

Dumitrescu A, Andric D, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a ablation study". Proc ICML 14(2023): 113-122. DOI: 10.4103/jrpp.jrpp_20_65

Eriksdottir B, Brankovic E, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a reproducibility study". Proc ICLR 16(2014): 124-134. DOI: 10.3389/fdgth.2026.1763884

Farkas I, Ionescu F, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a large-scale evaluation". ACM Trans Intell Syst 18(2017): 135-146. DOI: 10.2196/48297

Grabowski P, Petrescu G, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a case study". Data Min Knowl Discov 20(2020): 146-158. DOI: 10.1007/s00330-025-12031-z

Hendriksen W, Wojcik H, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a survey". Artif Intell 22(2023): 157-170. DOI: 10.3389/fdgth.2026.1699005

Ionescu F, Foscarini I, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a comparative analysis". Knowl Based Syst 24(2014): 168-182. DOI:

3389/fdgth.2026.1834800 10. Jankowiak G, Grabowski J, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a field deployment report". IEEE Trans Neural Netw Learn Syst 26(2017): 179-185. DOI: 10.2196/69678

Kowalczyk N, Novotna K, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a benchmark study". Proc KDD 28(2020): 190-197. DOI: 10.7759/cureus.46454

Lindqvist U, Urbanek L, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a systematic evaluation". Proc AAAI 30(2023): 201-209. DOI: 10.1016/j.ssci.2025.107028

Marchetti D, Doncheva M, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a empirical analysis". IEEE Trans Knowl Data Eng 32(2014): 212-221. DOI: 10.2196/48633

Novotna E, Eriksdottir N, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a ablation study". J Artif Intell Res 34(2017): 223-233. DOI: 10.1371/journal.pone.0305949

Ostrowski L, Lindqvist O, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a reproducibility study". ACM Comput Surv 36(2020): 234-245. DOI: 10.1371/journal.pdig.0000514

Petrescu S, Szabo P, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a large-scale evaluation". Neural Comput Appl 38(2023): 245-257. DOI: 10.17219/acem/208596

Quintero B, Balogh Q, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a case study". Expert Syst Appl 40(2014): 256-269. DOI: 10.7759/cureus.104086

Ristic C, Castellani R, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a survey". Inf Sci 42(2017): 267-281. DOI: 10.1038/s41746-023-00852-5

Szabo J, Jankowiak S, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a comparative analysis". Pattern Recognit 44(2020): 278-284. DOI: 10.1016/j.mayocpiqo.2022.09.004

Tarasov Q, Quintero T, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a field deployment report". IEEE Access 46(2023): 289-296. DOI: 10.1177/08404704241291226

Urbanek Z, Zielinski U, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a benchmark study". ACM Trans Softw Eng Methodol 8(2014): 300-308. DOI: 10.1093/medlaw/fwad013

Vasquez A, Alvez V, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a systematic evaluation". Proc MLSys 10(2017): 311-320. DOI: 10.2196/89834

Wojcik H, Hendriksen W, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a empirical analysis". Proc FAccT 12(2020): 322-332. DOI: 10.1007/s10916-024-02104-9

Zielinski O, Ostrowski Z, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a ablation study". Nat Mach Intell 14(2023): 333-344. DOI: 10.3389/fdgth.2026.1896184

Andric V, Vasquez A, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a reproducibility study". J Mach Learn Res 16(2014): 344-356. DOI: 10.3390/diagnostics15162117

Balogh E, Emmerich B, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a large-scale evaluation". IEEE Trans Pattern Anal Mach Intell 18(2017): 355-368. DOI: 10.4103/jrpp.jrpp_20_65

Chiriac F, Farkas C, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a case study". Proc NeurIPS 20(2020): 366-380. DOI: 10.3389/fdgth.2026.1763884

Doncheva M, Marchetti D, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a survey". Proc ICML 22(2023): 377-383. DOI: 10.2196/48297

Emmerich T, Tarasov E, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a comparative analysis". Proc ICLR 24(2014): 388-395. DOI: 10.1007/s00330-025-12031-z

Foscarini C, Chiriac F, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a field deployment report". ACM Trans Intell Syst 26(2017): 399-407. DOI: 10.3389/fdgth.2026.1699005

Alvez D, Dumitrescu A, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a benchmark study". Data Min Knowl Discov 28(2020): 410-419. DOI: 10.3389/fdgth.2026.1834800

Brankovic K, Kowalczyk B, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a systematic evaluation". Artif Intell 30(2023): 421-431. DOI: 10.2196/69678

Castellani R, Ristic C, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a empirical analysis". Knowl Based Syst 32(2014): 432-443. DOI: 10.7759/cureus.46454

Dumitrescu A, Andric D, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a ablation study". IEEE Trans Neural Netw Learn Syst 34(2017): 443-455. DOI: 10.1016/j.ssci.2025.107028

Eriksdottir B, Brankovic E, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a reproducibility study". Proc KDD 36(2020): 454-467. DOI: 10.2196/48633

Farkas I, Ionescu F, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a large-scale evaluation". Proc AAAI 38(2023): 465-479. DOI: 10.1371/journal.pone.0305949

Grabowski P, Petrescu G, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a case study". IEEE Trans Knowl Data Eng 40(2014): 476-482. DOI: 10.1371/journal.pdig.0000514

Hendriksen W, Wojcik H, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a survey". J Artif Intell Res 42(2017): 487-494. DOI: 10.17219/acem/208596

Ionescu F, Foscarini I, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a comparative analysis". ACM Comput Surv 44(2020): 498-506. DOI: 10.7759/cureus.104086

Jankowiak G, Grabowski J, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a field deployment report". Neural Comput Appl 46(2023): 509-518. DOI: 10.1038/s41746-023-00852-5

Kowalczyk N, Novotna K, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a benchmark study". Expert Syst Appl 8(2014): 520-530. DOI: 10.1016/j.mayocpiqo.2022.09.004

Lindqvist U, Urbanek L, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a systematic evaluation". Inf Sci 10(2017): 531-542. DOI: 10.1177/08404704241291226

Marchetti D, Doncheva M, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a empirical analysis". Pattern Recognit 12(2020): 542-554. DOI: 10.1093/medlaw/fwad013

Novotna E, Eriksdottir N, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a ablation study". IEEE Access 14(2023): 553-566. DOI: 10.2196/89834

Ostrowski L, Lindqvist O, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a reproducibility study". ACM Trans Softw Eng Methodol 16(2014): 564-578. DOI: 10.1007/s10916-024-02104-9

Petrescu S, Szabo P, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a large-scale evaluation". Proc MLSys 18(2017): 575-581. DOI: 10.3389/fdgth.2026.1896184

Quintero B, Balogh Q, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a case study". Proc FAccT 20(2020): 586-593. DOI: 10.3390/diagnostics15162117

Ristic C, Castellani R, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a survey". Nat Mach Intell 22(2023): 597-605. DOI: 10.4103/jrpp.jrpp_20_65

Szabo J, Jankowiak S, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a comparative analysis". J Mach Learn Res 24(2014): 608-617. DOI: 10.3389/fdgth.2026.1763884

Tarasov Q, Quintero T, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a field deployment report". IEEE Trans Pattern Anal Mach Intell 26(2017): 619-629. DOI: 10.2196/48297

Urbanek Z, Zielinski U, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a benchmark study". Proc NeurIPS 28(2020): 630-641. DOI: 10.1007/s00330-025-12031-z

Vasquez A, Alvez V, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a systematic evaluation". Proc ICML 30(2023): 641-653. DOI: 10.3389/fdgth.2026.1699005

Wojcik H, Hendriksen W, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a empirical analysis". Proc ICLR 32(2014): 652-665. DOI: 10.3389/fdgth.2026.1834800

Zielinski O, Ostrowski Z, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a ablation study". ACM Trans Intell Syst 34(2017): 663-677. DOI: 10.2196/69678

Andric V, Vasquez A, et al. "Traffic Signal Control With Multi-Agent Reinforcement Learning: a reproducibility study". Data Min Knowl Discov 36(2020): 674-680. DOI: 10.7759/cureus.46454

Downloads

Published

2025-04-22

Issue

Vol. 4 No. 1 (2025): vol 4 issue 1 2025

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.