{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/traffic-signal-control","name":"Traffic Signal Control","slug":"traffic-signal-control","description_markdown":"Control traffic lights/signals to optimize traffic.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Flaticon](https://www.flaticon.com/free-icon/traffic-light_2760947) )</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":201,"papers_with_code":62,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/autonomous-vehicles","name":"Autonomous Vehicles"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":201,"of_with_code":62,"tagged_in_all":201,"counts":{"archive_papers_tagged":201,"with_a_code_link":62,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":201,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/colight-learning-network-level-cooperation","slug":"colight-learning-network-level-cooperation","title":"CoLight: Learning Network-level Cooperation for Traffic Signal Control","date":"2019-05-11","arxiv_id":"1905.05717","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colight-learning-network-level-cooperation#ran","syntology_url":"https://syntology.ai/paper/1905.05717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05717"}},"official":{"repos":["wingsweihua/colight"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-variationally-intrinsic-motivated","slug":"meta-variationally-intrinsic-motivated","title":"MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control","date":"2021-01-04","arxiv_id":"2101.00746","repositories_listed":3,"syntology":null},{"url":"/paper/illm-tsc-integration-reinforcement-learning","slug":"illm-tsc-integration-reinforcement-learning","title":"iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement","date":"2024-07-08","arxiv_id":"2407.06025","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-control-and-coordinate-hybrid","slug":"learning-to-control-and-coordinate-hybrid","title":"Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections","date":"2023-01-12","arxiv_id":"2301.05294","repositories_listed":2,"syntology":null},{"url":"/paper/libsignal-an-open-library-for-traffic-signal","slug":"libsignal-an-open-library-for-traffic-signal","title":"LibSignal: An Open Library for Traffic Signal Control","date":"2022-11-19","arxiv_id":"2211.10649","repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-intensive-state-design-for-traffic","slug":"knowledge-intensive-state-design-for-traffic","title":"Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization","date":"2021-12-30","arxiv_id":"2201.00006","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-pressure-improving-efficiency-for","slug":"efficient-pressure-improving-efficiency-for","title":"Efficient Pressure: Improving efficiency for signalized intersections","date":"2021-12-04","arxiv_id":"2112.02336","repositories_listed":2,"syntology":null},{"url":"/paper/congested-urban-networks-tend-to-be","slug":"congested-urban-networks-tend-to-be","title":"Congested Urban Networks Tend to Be Insensitive to Signal Settings: Implications for Learning-Based Control","date":"2020-08-21","arxiv_id":"2008.10989","repositories_listed":2,"syntology":null},{"url":"/paper/joint-pedestrian-and-vehicle-traffic","slug":"joint-pedestrian-and-vehicle-traffic","title":"Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.05018","repositories_listed":1,"syntology":null},{"url":"/paper/a-constrained-multi-agent-reinforcement","slug":"a-constrained-multi-agent-reinforcement","title":"A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control","date":"2025-03-30","arxiv_id":"2503.23626","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-phase-pressure-control-enhanced","slug":"generalized-phase-pressure-control-enhanced","title":"Generalized Phase Pressure Control Enhanced Reinforcement Learning for Traffic Signal Control","date":"2025-03-26","arxiv_id":"2503.20205","repositories_listed":1,"syntology":null},{"url":"/paper/a-parallel-hybrid-action-space-reinforcement","slug":"a-parallel-hybrid-action-space-reinforcement","title":"A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control","date":"2025-03-18","arxiv_id":"2503.14250","repositories_listed":1,"syntology":null},{"url":"/paper/collmlight-cooperative-large-language-model","slug":"collmlight-cooperative-large-language-model","title":"CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control","date":"2025-03-14","arxiv_id":"2503.11739","repositories_listed":1,"syntology":null},{"url":"/paper/maclight-multi-scene-aggregation","slug":"maclight-multi-scene-aggregation","title":"MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control","date":"2024-12-20","arxiv_id":"2412.15703","repositories_listed":1,"syntology":null},{"url":"/paper/difflight-a-partial-rewards-conditioned","slug":"difflight-a-partial-rewards-conditioned","title":"DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data","date":"2024-10-30","arxiv_id":"2410.22938","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/difflight-a-partial-rewards-conditioned#ran","syntology_url":"https://syntology.ai/paper/2410.22938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22938"}},"official":{"repos":["lokol5579/DiffLight-release"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pytsc-a-unified-platform-for-multi-agent","slug":"pytsc-a-unified-platform-for-multi-agent","title":"PyTSC: A Unified Platform for Multi-Agent Reinforcement Learning in Traffic Signal Control","date":"2024-10-23","arxiv_id":"2410.18202","repositories_listed":1,"syntology":null},{"url":"/paper/syntrac-a-synthetic-dataset-for-traffic","slug":"syntrac-a-synthetic-dataset-for-traffic","title":"SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras","date":"2024-08-18","arxiv_id":"2408.09588","repositories_listed":1,"syntology":null},{"url":"/paper/guidelight-industrial-solution-guidance-for","slug":"guidelight-industrial-solution-guidance-for","title":"GuideLight: \"Industrial Solution\" Guidance for More Practical Traffic Signal Control Agents","date":"2024-07-15","arxiv_id":"2407.10811","repositories_listed":1,"syntology":null},{"url":"/paper/a-gpu-accelerated-large-scale-simulator-for","slug":"a-gpu-accelerated-large-scale-simulator-for","title":"A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking","date":"2024-06-15","arxiv_id":"2406.10661","repositories_listed":1,"syntology":null},{"url":"/paper/traffic-signal-cycle-control-with-centralized","slug":"traffic-signal-cycle-control-with-centralized","title":"Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies","date":"2024-06-12","arxiv_id":"2406.08248","repositories_listed":1,"syntology":null},{"url":"/paper/coslight-co-optimizing-collaborator-selection","slug":"coslight-co-optimizing-collaborator-selection","title":"CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control","date":"2024-05-27","arxiv_id":"2405.17152","repositories_listed":1,"syntology":null},{"url":"/paper/x-light-cross-city-traffic-signal-control","slug":"x-light-cross-city-traffic-signal-control","title":"X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner","date":"2024-04-18","arxiv_id":"2404.12090","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/x-light-cross-city-traffic-signal-control#ran","syntology_url":"https://syntology.ai/paper/2404.12090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12090"}},"official":{"repos":["jianghaoyuan1994/x-light"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-multi-agent-reinforcement-learning-3","slug":"towards-multi-agent-reinforcement-learning-3","title":"Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs","date":"2024-04-17","arxiv_id":"2404.11014","repositories_listed":1,"syntology":null},{"url":"/paper/llm-assisted-light-leveraging-large-language","slug":"llm-assisted-light-leveraging-large-language","title":"LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments","date":"2024-03-13","arxiv_id":"2403.08337","repositories_listed":1,"syntology":null},{"url":"/paper/open-ti-open-traffic-intelligence-with","slug":"open-ti-open-traffic-intelligence-with","title":"Open-TI: Open Traffic Intelligence with Augmented Language Model","date":"2023-12-30","arxiv_id":"2401.00211","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/open-ti-open-traffic-intelligence-with#ran","syntology_url":"https://syntology.ai/paper/2401.00211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00211"}},"official":{"repos":["darl-libsignal/openti"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-as-traffic-signal","slug":"large-language-models-as-traffic-signal","title":"LLMLight: Large Language Models as Traffic Signal Control Agents","date":"2023-12-26","arxiv_id":"2312.16044","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-as-traffic-signal#ran","syntology_url":"https://syntology.ai/paper/2312.16044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16044"}},"official":{"repos":["usail-hkust/llmtscs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dualight-enhancing-traffic-signal-control-by","slug":"dualight-enhancing-traffic-signal-control-by","title":"DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledge","date":"2023-12-22","arxiv_id":"2312.14532","repositories_listed":1,"syntology":null},{"url":"/paper/feedback-feedforward-signal-control-with","slug":"feedback-feedforward-signal-control-with","title":"Feedback-feedforward Signal Control with Exogenous Demand Estimation in Congested Urban Road Networks","date":"2023-12-12","arxiv_id":"2312.07359","repositories_listed":1,"syntology":null},{"url":"/paper/traffic-signal-control-using-lightweight","slug":"traffic-signal-control-using-lightweight","title":"Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach","date":"2023-12-12","arxiv_id":"2312.07795","repositories_listed":1,"syntology":null},{"url":"/paper/unitsa-a-universal-reinforcement-learning","slug":"unitsa-a-universal-reinforcement-learning","title":"UniTSA: A Universal Reinforcement Learning Framework for V2X Traffic Signal Control","date":"2023-12-08","arxiv_id":"2312.05090","repositories_listed":1,"syntology":null},{"url":"/paper/llm-powered-sim-to-real-transfer-for-traffic","slug":"llm-powered-sim-to-real-transfer-for-traffic","title":"Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning","date":"2023-08-28","arxiv_id":"2308.14284","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/llm-powered-sim-to-real-transfer-for-traffic#ran","syntology_url":"https://syntology.ai/paper/2308.14284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14284"}},"official":{"repos":["darl-libsignal/promptgat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/uncertainty-aware-grounded-action","slug":"uncertainty-aware-grounded-action","title":"Uncertainty-aware Grounded Action Transformation towards Sim-to-Real Transfer for Traffic Signal Control","date":"2023-07-23","arxiv_id":"2307.12388","repositories_listed":1,"syntology":null},{"url":"/paper/denselight-efficient-control-for-large-scale","slug":"denselight-efficient-control-for-large-scale","title":"DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback","date":"2023-06-13","arxiv_id":"2306.07553","repositories_listed":1,"syntology":null},{"url":"/paper/tackling-unbounded-state-spaces-in-continuing","slug":"tackling-unbounded-state-spaces-in-continuing","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","date":"2023-06-02","arxiv_id":"2306.01896","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":1,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tackling-unbounded-state-spaces-in-continuing#ran","syntology_url":"https://syntology.ai/paper/2306.01896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01896"}},"official":{"repos":["badger-rl/stop"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-approaches-for-traffic","slug":"reinforcement-learning-approaches-for-traffic","title":"Reinforcement Learning Approaches for Traffic Signal Control under Missing Data","date":"2023-04-21","arxiv_id":"2304.10722","repositories_listed":1,"syntology":null},{"url":"/paper/humanlight-incentivizing-ridesharing-via","slug":"humanlight-incentivizing-ridesharing-via","title":"HumanLight: Incentivizing Ridesharing via Human-centric Deep Reinforcement Learning in Traffic Signal Control","date":"2023-04-05","arxiv_id":"2304.03697","repositories_listed":1,"syntology":null},{"url":"/paper/data-might-be-enough-bridge-real-world","slug":"data-might-be-enough-bridge-real-world","title":"DataLight: Offline Data-Driven Traffic Signal Control","date":"2023-03-20","arxiv_id":"2303.10828","repositories_listed":1,"syntology":null},{"url":"/paper/safelight-a-reinforcement-learning-method","slug":"safelight-a-reinforcement-learning-method","title":"SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control","date":"2022-11-20","arxiv_id":"2211.10871","repositories_listed":1,"syntology":null},{"url":"/paper/dynamiclight-dynamically-tuning-traffic","slug":"dynamiclight-dynamically-tuning-traffic","title":"DynamicLight: Two-Stage Dynamic Traffic Signal Timing","date":"2022-11-02","arxiv_id":"2211.01025","repositories_listed":1,"syntology":null},{"url":"/paper/adlight-a-universal-approach-of-traffic","slug":"adlight-a-universal-approach-of-traffic","title":"ADLight: A Universal Approach of Traffic Signal Control with Augmented Data Using Reinforcement Learning","date":"2022-10-24","arxiv_id":"2210.13378","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-network-level-traffic-flow","slug":"modeling-network-level-traffic-flow","title":"Modeling Network-level Traffic Flow Transitions on Sparse Data","date":"2022-08-13","arxiv_id":"2208.06646","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-graph-reinforcement-learning-for","slug":"model-based-graph-reinforcement-learning-for","title":"Model-based graph reinforcement learning for inductive traffic signal control","date":"2022-08-01","arxiv_id":"2208.00659","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-11","slug":"multi-agent-reinforcement-learning-for-11","title":"Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method","date":"2022-04-26","arxiv_id":"2204.12190","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-in-possibly","slug":"reinforcement-learning-in-possibly","title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","date":"2022-03-03","arxiv_id":"2203.01707","repositories_listed":1,"syntology":null},{"url":"/paper/expression-is-enough-improving-traffic-signal","slug":"expression-is-enough-improving-traffic-signal","title":"Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control","date":"2021-12-19","arxiv_id":"2112.10107","repositories_listed":1,"syntology":null},{"url":"/paper/delayed-propagation-transformer-a-universal","slug":"delayed-propagation-transformer-a-universal","title":"Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems","date":"2021-10-29","arxiv_id":"2110.15926","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/delayed-propagation-transformer-a-universal#ran","syntology_url":"https://syntology.ai/paper/2110.15926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15926"}},"official":{"repos":["vita-group/dept"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-q-learning-for-intelligent","slug":"deep-reinforcement-q-learning-for-intelligent","title":"Deep Reinforcement Q-Learning for Intelligent Traffic Signal Control with Partial Detection","date":"2021-09-29","arxiv_id":"2109.14337","repositories_listed":1,"syntology":null},{"url":"/paper/back-to-basics-deep-reinforcement-learning-in","slug":"back-to-basics-deep-reinforcement-learning-in","title":"Back to Basics: Deep Reinforcement Learning in Traffic Signal Control","date":"2021-09-15","arxiv_id":"2109.07180","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-algorithms-for-1","slug":"a-comparative-study-of-algorithms-for-1","title":"A Comparative Study of Algorithms for Intelligent Traffic Signal Control","date":"2021-09-02","arxiv_id":"2109.00937","repositories_listed":1,"syntology":null},{"url":"/paper/dqn-control-solution-for-kdd-cup-2021-city","slug":"dqn-control-solution-for-kdd-cup-2021-city","title":"DQN Control Solution for KDD Cup 2021 City Brain Challenge","date":"2021-08-14","arxiv_id":"2108.06491","repositories_listed":1,"syntology":null},{"url":"/paper/independent-reinforcement-learning-for-weakly","slug":"independent-reinforcement-learning-for-weakly","title":"Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem","date":"2021-04-22","arxiv_id":"2104.10917","repositories_listed":1,"syntology":null},{"url":"/paper/lemgorl-an-open-source-benchmark-tool-to","slug":"lemgorl-an-open-source-benchmark-tool-to","title":"Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control","date":"2021-03-30","arxiv_id":"2103.16223","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-traffic-signal-control-using-queue","slug":"a-simple-traffic-signal-control-using-queue","title":"A Simple Traffic Signal Control Using Queue Length Information","date":"2020-06-11","arxiv_id":"2006.06337","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-2","slug":"multi-agent-reinforcement-learning-for-2","title":"Multi-agent Reinforcement Learning for Networked System Control","date":"2020-04-03","arxiv_id":"2004.01339","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":14,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":16,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/multi-agent-reinforcement-learning-for-2#ran","syntology_url":"https://syntology.ai/paper/2004.01339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01339"}},"official":{"repos":["cts198859/deeprl_network"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/ig-rl-inductive-graph-reinforcement-learning","slug":"ig-rl-inductive-graph-reinforcement-learning","title":"IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control","date":"2020-03-06","arxiv_id":"2003.05738","repositories_listed":1,"syntology":null},{"url":"/paper/gamma-reward-a-novel-multi-agent","slug":"gamma-reward-a-novel-multi-agent","title":"Learning Scalable Multi-Agent Coordination by Spatial Differentiation for Traffic Signal Control","date":"2020-02-27","arxiv_id":"2002.11874","repositories_listed":1,"syntology":null},{"url":"/paper/learning-an-interpretable-traffic-signal","slug":"learning-an-interpretable-traffic-signal","title":"Learning an Interpretable Traffic Signal Control Policy","date":"2019-12-23","arxiv_id":"1912.11023","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-source-framework-for-adaptive-traffic","slug":"an-open-source-framework-for-adaptive-traffic","title":"An Open-Source Framework for Adaptive Traffic Signal Control","date":"2019-09-01","arxiv_id":"1909.00395","repositories_listed":1,"syntology":null},{"url":"/paper/cityflow-a-multi-agent-reinforcement-learning","slug":"cityflow-a-multi-agent-reinforcement-learning","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","date":"2019-05-13","arxiv_id":"1905.05217","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cityflow-a-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1905.05217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05217"}},"official":{"repos":["cityflow-project/CityFlow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-phase-competition-for-traffic-signal","slug":"learning-phase-competition-for-traffic-signal","title":"Learning Phase Competition for Traffic Signal Control","date":"2019-05-12","arxiv_id":"1905.04722","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-phase-competition-for-traffic-signal#ran","syntology_url":"https://syntology.ai/paper/1905.04722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04722"}},"official":null}},{"url":"/paper/towards-robust-deep-reinforcement-learning","slug":"towards-robust-deep-reinforcement-learning","title":"Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures","date":"2019-04-17","arxiv_id":"1904.08353","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-deep-reinforcement-learning-for-2","slug":"multi-agent-deep-reinforcement-learning-for-2","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","date":"2019-03-11","arxiv_id":"1903.04527","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-agent-deep-reinforcement-learning-for-2#ran","syntology_url":"https://syntology.ai/paper/1903.04527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04527"}},"official":{"repos":["cts198859/deeprl_signal_control"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":null,"slug":"hilight-a-hierarchical-reinforcement-learning","title":"HiLight: A Hierarchical Reinforcement Learning Framework with Global Adversarial Guidance for Large-Scale Traffic Signal Control","date":"2025-06-17","arxiv_id":"2506.14391","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-of-reinforcement-learning-based","title":"Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Study","date":"2025-06-16","arxiv_id":"2506.13836","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlmlight-traffic-signal-control-via-vision","title":"VLMLight: Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning","date":"2025-05-26","arxiv_id":"2505.19486","repositories_listed":0,"syntology":null},{"url":null,"slug":"cv-mp-max-pressure-control-in-heterogeneously","title":"CV-MP: Max-Pressure Control in Heterogeneously Distributed and Partially Connected Vehicle Environments","date":"2025-05-08","arxiv_id":"2505.05258","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-location-search-for-identifying","title":"Dynamic Location Search for Identifying Maximum Weighted Independent Sets in Complex Networks","date":"2025-05-07","arxiv_id":"2505.04674","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-hierarchical-reinforcement-learning","title":"Federated Hierarchical Reinforcement Learning for Adaptive Traffic Signal Control","date":"2025-04-07","arxiv_id":"2504.05553","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-and-efficient-coexistence-of-autonomous","title":"Safe and Efficient Coexistence of Autonomous Vehicles with Human-Driven Traffic at Signalized Intersections","date":"2025-04-07","arxiv_id":"2504.05101","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-framework-for-turning","title":"Domain Adaptation Framework for Turning Movement Count Estimation with Limited Data","date":"2025-03-25","arxiv_id":"2503.20113","repositories_listed":0,"syntology":null},{"url":null,"slug":"unicorn-a-universal-and-collaborative","title":"Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control","date":"2025-03-14","arxiv_id":"2503.11488","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-model-predictive-control-for-traffic","title":"Adaptive model predictive control for traffic signal timing with unknown demand and parameters","date":"2025-03-13","arxiv_id":"2503.10934","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-regional-traffic-signal-control","title":"Large-scale Regional Traffic Signal Control Based on Single-Agent Reinforcement Learning","date":"2025-03-12","arxiv_id":"2503.09252","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-traffic-signal-control-through","title":"Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse","date":"2025-03-11","arxiv_id":"2503.08728","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-a-single-actor-to-output-personalized","title":"Using a single actor to output personalized policy for different intersections","date":"2025-03-10","arxiv_id":"2503.07678","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamerv3-for-traffic-signal-control","title":"DreamerV3 for Traffic Signal Control: Hyperparameter Tuning and Performance","date":"2025-03-04","arxiv_id":"2503.02279","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-dependency-dynamics-in-multi-agent","title":"Toward Dependency Dynamics in Multi-Agent Reinforcement Learning for Traffic Signal Control","date":"2025-02-23","arxiv_id":"2502.16608","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-strategy-on-macro-and-micro","title":"Communication Strategy on Macro-and-Micro Traffic State in Cooperative Deep Reinforcement Learning for Regional Traffic Signal Control","date":"2025-02-18","arxiv_id":"2502.13248","repositories_listed":0,"syntology":null},{"url":null,"slug":"fitlight-federated-imitation-learning-for","title":"FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control","date":"2025-02-17","arxiv_id":"2502.11937","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzylight-a-robust-two-stage-fuzzy-approach","title":"FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities","date":"2025-01-27","arxiv_id":"2501.15820","repositories_listed":0,"syntology":null},{"url":null,"slug":"amm-adaptive-modularized-reinforcement-model","title":"AMM: Adaptive Modularized Reinforcement Model for Multi-city Traffic Signal Control","date":"2025-01-05","arxiv_id":"2501.02548","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrated-strategy-for-urban-traffic","title":"Integrated Strategy for Urban Traffic Optimization: Prediction, Adaptive Signal Control, and Distributed Communication via Messaging","date":"2025-01-02","arxiv_id":"2501.02008","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-conditioned-data-augmentation-for","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","date":"2024-12-29","arxiv_id":"2412.20519","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-critique-tune-based-reinforcement","title":"Bayesian Critique-Tune-Based Reinforcement Learning with Adaptive Pressure for Multi-Intersection Traffic Signal Control","date":"2024-12-18","arxiv_id":"2412.16225","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-intelligence-in-traffic-systems","title":"Artificial Intelligence in Traffic Systems","date":"2024-12-16","arxiv_id":"2412.12046","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-transfer-learning-framework-for","title":"Data-Driven Transfer Learning Framework for Estimating Turning Movement Counts","date":"2024-12-13","arxiv_id":"2412.09861","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferlight-zero-shot-traffic-signal","title":"TransferLight: Zero-Shot Traffic Signal Control on any Road-Network","date":"2024-12-12","arxiv_id":"2412.09719","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cav-based-perimeter-free-regional-traffic","title":"A CAV-based perimeter-free regional traffic control strategy utilizing existing parking infrastructure","date":"2024-12-05","arxiv_id":"2412.04620","repositories_listed":0,"syntology":null},{"url":null,"slug":"intersection-aware-assessment-of-ems","title":"Intersection-Aware Assessment of EMS Accessibility in NYC: A Data-Driven Approach","date":"2024-12-05","arxiv_id":"2412.04369","repositories_listed":0,"syntology":null},{"url":null,"slug":"traffic-co-simulation-framework-empowered-by","title":"Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning","date":"2024-12-05","arxiv_id":"2412.03925","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-transit-signal-priority-into","title":"Integrating Transit Signal Priority into Multi-Agent Reinforcement Learning based Traffic Signal Control","date":"2024-11-28","arxiv_id":"2411.19359","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-traffic-signal-control-using-high","title":"Optimizing Traffic Signal Control using High-Dimensional State Representation and Efficient Deep Reinforcement Learning","date":"2024-11-12","arxiv_id":"2411.07759","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-hop-upstream-preemptive-traffic-signal","title":"Multi-hop Upstream Anticipatory Traffic Signal Control with Deep Reinforcement Learning","date":"2024-11-10","arxiv_id":"2411.07271","repositories_listed":0,"syntology":null},{"url":null,"slug":"offlight-an-offline-multi-agent-reinforcement","title":"OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control","date":"2024-11-10","arxiv_id":"2411.06601","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-multi-objective-optimization-for","title":"Scalable Multi-Objective Optimization for Robust Traffic Signal Control in Uncertain Environments","date":"2024-09-20","arxiv_id":"2409.13388","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-partial-observability-in-adaptive","title":"Mitigating Partial Observability in Adaptive Traffic Signal Control with Transformers","date":"2024-09-16","arxiv_id":"2409.10693","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-traffic-signal-control-using","title":"Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion","date":"2024-08-28","arxiv_id":"2408.15751","repositories_listed":0,"syntology":null},{"url":null,"slug":"mallight-influence-aware-coordinated-traffic","title":"MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions","date":"2024-08-19","arxiv_id":"2408.09768","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00814","title":"Adaptive traffic signal safety and efficiency improvement by multi objective deep reinforcement learning approach","date":"2024-08-01","arxiv_id":"2408.00814","repositories_listed":0,"syntology":null},{"url":null,"slug":"movelight-enhancing-traffic-signal-control","title":"MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning","date":"2024-07-24","arxiv_id":"2407.17303","repositories_listed":0,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/task/traffic-signal-control/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/traffic-signal-control/papers/2","json":"/task/traffic-signal-control/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/traffic-signal-control/papers/3","json":"/task/traffic-signal-control/papers/3.json","rows":1},{"order":"ran","page":1,"of":1,"url":"/task/traffic-signal-control/papers/ran/1","json":"/task/traffic-signal-control/papers/ran/1.json","rows":11}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e7dca834aaa967beead7ef7d283505dc85d5c1f72959a1b8351f7a29da935697","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}