{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:08:20Z","timestamp":1788890900136,"version":"build-2803163510"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Anhui Province's Dual Characteristics Construction Project","award":["2025XDCYXY001"],"award-info":[{"award-number":["2025XDCYXY001"]}]},{"name":"Anhui Province Characteristic Specialty (Group) Construction (Cultivation) Project","award":["2024TSZY001"],"award-info":[{"award-number":["2024TSZY001"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Emergency signal control has to clear emergency vehicles through intersections without creating excessive delay for ordinary traffic. Many existing controllers still depend on manually designed traffic features, and unfamiliar emergency patterns often require additional training before the control policy can be adjusted reliably. For this setting, a multi-agent meta-reinforcement learning framework is developed using Contrastive Predictive Coding (CPC) for traffic state representation. CPC compresses high-dimensional traffic sequences into compact representations that are subsequently used by intersection agents during few-sample policy adaptation. Agent communication is weighted by both distance and transmission delay, while hierarchical emergency priority control adjusts signal decisions according to event severity. Tests on the iTETRIS simulation platform with the CityFlow Emergency dataset produced an emergency response time of 25.3 s, an average regular vehicle delay of 80.5 s per vehicle, and a 98.2% emergency success rate in high-priority scenarios. In the ablation experiments, removing CPC caused the largest single performance loss, whereas the all-module configuration showed a 44.3% contribution to response-time reduction in the contribution analysis. Overall, the framework maintained emergency vehicle priority while keeping the effect on regular traffic within a comparatively limited range under the evaluated emergency conditions.<\/jats:p>","DOI":"10.1371\/journal.pone.0357779","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:31:55Z","timestamp":1788888715000},"page":"e0357779","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-agent meta-reinforcement learning based on contrastive predictive coding\u2014For rapid adaptive traffic control after emergencies"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9601-8201","authenticated-orcid":true,"given":"Wei","family":"Jiang","sequence":"first","affiliation":[{"name":"Anhui Sanlian University","place":["Hefei, Anhui, China"],"department":["Faculty of Intelligent Transportation"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Anhui Sanlian University","place":["Hefei, Anhui, China"],"department":["Faculty of Intelligent Transportation"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui Sanlian University","place":["Hefei, Anhui, China"],"department":["Faculty of Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruting","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui Sanlian University","place":["Hefei, Anhui, China"],"department":["Faculty of Intelligent Transportation"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Tang","sequence":"additional","affiliation":[{"name":"Anhui Sanlian University","place":["Hefei, Anhui, China"],"department":["Faculty of Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"pone.0357779.ref001","doi-asserted-by":"crossref","first-page":"105655","DOI":"10.1016\/j.aap.2020.105655","article-title":"Multi-Objective reinforcement learning approach for improving safety at intersections with adaptive traffic signal control","volume":"144","author":"Y Gong","year":"2020","journal-title":"Accid Anal Prev"},{"key":"pone.0357779.ref002","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.comcom.2020.03.005","article-title":"Traffic signal control for smart cities using reinforcement learning","volume":"154","author":"H Joo","year":"2020","journal-title":"Computer Communications"},{"key":"pone.0357779.ref003","doi-asserted-by":"crossref","first-page":"103046","DOI":"10.1016\/j.trc.2021.103046","article-title":"Adaptive Traffic Signal Control for large-scale scenario with Cooperative Group-based Multi-agent reinforcement learning","volume":"125","author":"T Wang","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"pone.0357779.ref004","doi-asserted-by":"crossref","first-page":"103059","DOI":"10.1016\/j.trc.2021.103059","article-title":"Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning","volume":"125","author":"Z Li","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"pone.0357779.ref005","doi-asserted-by":"crossref","first-page":"104165","DOI":"10.1016\/j.engappai.2021.104165","article-title":"Learning scalable multi-agent coordination by spatial differentiation for traffic signal control","volume":"100","author":"J Liu","year":"2021","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"7","key":"pone.0357779.ref006","doi-asserted-by":"crossref","first-page":"7496","DOI":"10.1109\/TITS.2021.3070835","article-title":"IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control","volume":"23","author":"F-X Devailly","year":"2022","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"15","key":"pone.0357779.ref007","doi-asserted-by":"crossref","first-page":"8605","DOI":"10.3390\/app15158605","article-title":"Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control with Spatio-Temporal Attention Mechanism","volume":"15","author":"W Jia","year":"2025","journal-title":"Applied Sciences"},{"key":"pone.0357779.ref008","doi-asserted-by":"crossref","first-page":"111602","DOI":"10.1016\/j.engappai.2025.111602","article-title":"Store-and-forward with graph attention: Enhanced multi-agent reinforcement learning for emergency-responsive traffic signal control","volume":"159","author":"K Yang","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0357779.ref009","doi-asserted-by":"crossref","first-page":"105019","DOI":"10.1016\/j.engappai.2022.105019","article-title":"A deep reinforcement learning-based cooperative approach for multi-intersection traffic signal control","volume":"114","author":"TA Haddad","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0357779.ref010","doi-asserted-by":"crossref","first-page":"108304","DOI":"10.1016\/j.knosys.2022.108304","article-title":"Distributed agent-based deep reinforcement learning for large scale traffic signal control","volume":"241","author":"Q Wu","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"pone.0357779.ref011","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.ins.2022.11.062","article-title":"Multi-agent broad reinforcement learning for intelligent traffic light control","volume":"619","author":"R Zhu","year":"2023","journal-title":"Information Sciences"},{"key":"pone.0357779.ref012","doi-asserted-by":"crossref","first-page":"119484","DOI":"10.1016\/j.ins.2023.119484","article-title":"Multiple intersections traffic signal control based on cooperative multi-agent reinforcement learning","volume":"647","author":"J Liu","year":"2023","journal-title":"Information Sciences"},{"key":"pone.0357779.ref013","doi-asserted-by":"crossref","first-page":"110440","DOI":"10.1016\/j.knosys.2023.110440","article-title":"Deep reinforcement learning for traffic signal control with consistent state and reward design approach","volume":"267","author":"S Bouktif","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"pone.0357779.ref014","doi-asserted-by":"crossref","first-page":"668","DOI":"10.51483\/IJAIML.6.5s.2026.668-674","article-title":"Context-Driven Adaptive Representation Learning For Intelligent Decision-Making In Smart City Traffic Management Applications","volume":"6","author":"S Antonibiya","year":"2026","journal-title":"IJAIML"},{"issue":"1","key":"pone.0357779.ref015","doi-asserted-by":"crossref","first-page":"19184","DOI":"10.1038\/s41598-023-46074-3","article-title":"A scalable approach to optimize traffic signal control with federated reinforcement learning","volume":"13","author":"J Bao","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0357779.ref016","first-page":"1","article-title":"A survey of large language models in transportation planning: modelling, design and decision-making","author":"Y Jin","year":"2026","journal-title":"Transportmetrica A: Transport Science"},{"issue":"2","key":"pone.0357779.ref017","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.3390\/su15021329","article-title":"A Resilient Intelligent Traffic Signal Control Scheme for Accident Scenario at Intersections via Deep Reinforcement Learning","volume":"15","author":"Z Zeinaly","year":"2023","journal-title":"Sustainability"},{"key":"pone.0357779.ref018","doi-asserted-by":"crossref","first-page":"103955","DOI":"10.1016\/j.trc.2022.103955","article-title":"EMVLight: A multi-agent reinforcement learning framework for an emergency vehicle decentralized routing and traffic signal control system","volume":"146","author":"H Su","year":"2023","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"pone.0357779.ref019","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.aej.2024.07.046","article-title":"Reinforcement learning based adaptive control method for traffic lights in intelligent transportation","volume":"106","author":"Z Huang","year":"2024","journal-title":"Alexandria Engineering Journal"},{"key":"pone.0357779.ref020","doi-asserted-by":"crossref","first-page":"111813","DOI":"10.1016\/j.engappai.2025.111813","article-title":"Cooperative traffic signal control for a partially observed vehicular network using multi-agent reinforcement learning","volume":"160","author":"C Wang","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0357779.ref021","doi-asserted-by":"crossref","first-page":"108526","DOI":"10.1016\/j.future.2026.108526","article-title":"Adaptive distributed multi-objective collaborative traffic signal control framework based on multi-agent reinforcement learning","volume":"184","author":"P Huang","year":"2026","journal-title":"Future Generation Computer Systems"},{"issue":"11","key":"pone.0357779.ref022","doi-asserted-by":"crossref","first-page":"15947","DOI":"10.1109\/TITS.2024.3410023","article-title":"Learning Multi-Intersection Traffic Signal Control via Coevolutionary Multi-Agent Reinforcement Learning","volume":"25","author":"W Chen","year":"2024","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"6","key":"pone.0357779.ref023","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1111\/mice.12924","article-title":"A meta\u2013reinforcement learning algorithm for traffic signal control to automatically switch different reward functions according to the saturation level of traffic flows","volume":"38","author":"G Kim","year":"2023","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"17","key":"pone.0357779.ref024","doi-asserted-by":"crossref","first-page":"28496","DOI":"10.1109\/JIOT.2024.3401829","article-title":"Adaptive Broad Deep Reinforcement Learning for Intelligent Traffic Light Control","volume":"11","author":"R Zhu","year":"2024","journal-title":"IEEE Internet Things J"},{"issue":"5","key":"pone.0357779.ref025","doi-asserted-by":"crossref","first-page":"114","DOI":"10.3390\/infrastructures10050114","article-title":"Traffic Signal Control via Reinforcement Learning: A Review on Applications and Innovations","volume":"10","author":"P Michailidis","year":"2025","journal-title":"Infrastructures"},{"issue":"1","key":"pone.0357779.ref026","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TITS.2022.3216203","article-title":"Distributed Signal Control of Arterial Corridors Using Multi-Agent Deep Reinforcement Learning","volume":"24","author":"W Zhang","year":"2023","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"pone.0357779.ref027","doi-asserted-by":"crossref","first-page":"120805","DOI":"10.1016\/j.ins.2024.120805","article-title":"Intelligent emergency traffic signal control system with pedestrian access","volume":"679","author":"L-J Liu","year":"2024","journal-title":"Information Sciences"},{"key":"pone.0357779.ref028","article-title":"A Systematic Review of Traditional and Reinforcement Learning-Based Traffic Signal Control Methods","author":"R Manikandan","year":"2026","journal-title":"Arch Computat Methods Eng"},{"key":"pone.0357779.ref029","article-title":"TrafCopAgent: synergizing reinforcement learning and multi-agent collaboration for adaptive emergency traffic control","author":"Y Fan","year":"2026","journal-title":"Sci Rep"},{"key":"pone.0357779.ref030","doi-asserted-by":"crossref","first-page":"109166","DOI":"10.1016\/j.knosys.2022.109166","article-title":"Meta-learning based spatial-temporal graph attention network for traffic signal control","volume":"250","author":"M Wang","year":"2022","journal-title":"Knowledge-Based Systems"},{"issue":"9","key":"pone.0357779.ref031","doi-asserted-by":"crossref","first-page":"1987","DOI":"10.1109\/JAS.2024.124365","article-title":"Regional Multi-Agent Cooperative Reinforcement Learning for City-Level Traffic Grid Signal Control","volume":"11","author":"Y Li","year":"2024","journal-title":"IEEE\/CAA J Autom Sinica"},{"issue":"2","key":"pone.0357779.ref032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3749378","article-title":"Fair Multi-Agent Reinforcement Learning for Traffic Control","volume":"3","author":"U Siddique","year":"2025","journal-title":"ACM J Auton Transport Syst"},{"issue":"8","key":"pone.0357779.ref033","doi-asserted-by":"crossref","first-page":"7457","DOI":"10.1609\/aaai.v35i8.16914","article-title":"Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning","volume":"35","author":"H Fu","year":"2021","journal-title":"AAAI"},{"issue":"1","key":"pone.0357779.ref034","doi-asserted-by":"crossref","first-page":"7612","DOI":"10.1038\/s41598-026-37722-5","article-title":"Multi-modal and multi-agent reinforcement learning framework for urban traffic flow prediction and signal control optimization","volume":"16","author":"R Wang","year":"2026","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0357779.ref035","doi-asserted-by":"crossref","DOI":"10.1049\/itr2.70296","article-title":"Coordination in Traffic Signal Control: A Mechanism\u2010Oriented Survey of Multi\u2010Agent Learning Approaches","volume":"20","author":"Q Xiong","year":"2026","journal-title":"IET Intelligent Trans Sys"},{"issue":"7","key":"pone.0357779.ref036","doi-asserted-by":"crossref","first-page":"8014","DOI":"10.1609\/aaai.v37i7.25969","article-title":"Learnable Path in Neural Controlled Differential Equations","volume":"37","author":"SY Jhin","year":"2023","journal-title":"AAAI"},{"key":"pone.0357779.ref037","doi-asserted-by":"crossref","unstructured":"Zhang J, Bedi AS, Wang M. Multi-agent reinforcement learning with general utilities via decentralized shadow reward actor-critic. 2022.","DOI":"10.1609\/aaai.v36i8.20887"},{"issue":"17","key":"pone.0357779.ref038","doi-asserted-by":"crossref","first-page":"6504","DOI":"10.3390\/s22176504","article-title":"Visual Pretraining via Contrastive Predictive Model for Pixel-Based Reinforcement Learning","volume":"22","author":"TM Luu","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"3","key":"pone.0357779.ref039","article-title":"Action-driven contrastive representation for reinforcement learning","volume":"17","author":"M Kim","year":"2022","journal-title":"PLoS One"},{"issue":"9","key":"pone.0357779.ref040","article-title":"A few-shot detection method for new types of network traffic attacks based on meta-learning with cross-attention","volume":"81","author":"K Shi","year":"2025","journal-title":"J Supercomput"},{"issue":"8","key":"pone.0357779.ref041","doi-asserted-by":"crossref","first-page":"112999","DOI":"10.1016\/j.celrep.2023.112999","article-title":"Adaptive expression of engrams by retroactive interference","volume":"42","author":"L Autore","year":"2023","journal-title":"Cell Rep"},{"key":"pone.0357779.ref042","doi-asserted-by":"crossref","unstructured":"Chen S, Ge C, Tong Z, Wang J, Song Y, Wang J, et al. AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition. In: Advances in Neural Information Processing Systems 35, 2022. 16664\u201378. https:\/\/doi.org\/10.52202\/068431-1212","DOI":"10.52202\/068431-1212"},{"key":"pone.0357779.ref043","doi-asserted-by":"crossref","first-page":"929348","DOI":"10.3389\/fncom.2022.929348","article-title":"Efficient Temporal Coding in the Early Visual System: Existing Evidence and Future Directions","volume":"16","author":"BH Price","year":"2022","journal-title":"Front Comput Neurosci"},{"issue":"11","key":"pone.0357779.ref044","doi-asserted-by":"crossref","first-page":"15229","DOI":"10.1109\/TITS.2024.3440474","article-title":"A Review on Emergency Vehicle Management for Intelligent Transportation Systems","volume":"25","author":"Naren","year":"2024","journal-title":"IEEE Trans Intell Transport Syst"},{"issue":"7","key":"pone.0357779.ref045","article-title":"Few-shot network intrusion detection method based on multi-domain fusion and cross-attention","volume":"20","author":"C Xu","year":"2025","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:32:08Z","timestamp":1788888728000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357779"}},"subtitle":[],"editor":[{"given":"Zhihong (Arry)","family":"Yao","sequence":"first","affiliation":[{"name":"Southwest Jiaotong University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357779","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]}}}