{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3QX237ZV6VG3UV6CQLAUXU2A5P","short_pith_number":"pith:3QX237ZV","schema_version":"1.0","canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","source":{"kind":"arxiv","id":"1908.03761","version":2},"attestation_state":"computed","paper":{"title":"Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Liangjun Ke, Xiaoqiang Wang, Xinghua Chai, Zhimin Qiao","submitted_at":"2019-08-10T14:19:21Z","abstract_excerpt":"Finding the optimal signal timing strategy is a difficult task for the problem of large-scale traffic signal control (TSC). Multi-Agent Reinforcement Learning (MARL) is a promising method to solve this problem. However, there is still room for improvement in extending to large-scale problems and modeling the behaviors of other agents for each individual agent. In this paper, a new MARL, called Cooperative double Q-learning (Co-DQL), is proposed, which has several prominent features. It uses a highly scalable independent double Q-learning method based on double estimators and the UCB policy, wh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1908.03761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-10T14:19:21Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"1e68ee2310b256b4b4c138e81da125225f78a7989f3220484282800013ab5267","abstract_canon_sha256":"9b2e82151eece2e0c687a4892da10e60574783808d2dea8a1d405bdf15a26deb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:19.944493Z","signature_b64":"fMiXFeSh7DXgreJZp1CYeL3Nsx3yW+93/bu2VrNCMIswADfNe/Kf1ZnjfsNBb/BHJyyCL455afNkzC8I2QyoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","last_reissued_at":"2026-07-05T03:13:19.944064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:19.944064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Liangjun Ke, Xiaoqiang Wang, Xinghua Chai, Zhimin Qiao","submitted_at":"2019-08-10T14:19:21Z","abstract_excerpt":"Finding the optimal signal timing strategy is a difficult task for the problem of large-scale traffic signal control (TSC). Multi-Agent Reinforcement Learning (MARL) is a promising method to solve this problem. However, there is still room for improvement in extending to large-scale problems and modeling the behaviors of other agents for each individual agent. In this paper, a new MARL, called Cooperative double Q-learning (Co-DQL), is proposed, which has several prominent features. It uses a highly scalable independent double Q-learning method based on double estimators and the UCB policy, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03761","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.03761/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1908.03761","created_at":"2026-07-05T03:13:19.944120+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03761v2","created_at":"2026-07-05T03:13:19.944120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03761","created_at":"2026-07-05T03:13:19.944120+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QX237ZV6VG3","created_at":"2026-07-05T03:13:19.944120+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QX237ZV6VG3UV6C","created_at":"2026-07-05T03:13:19.944120+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QX237ZV","created_at":"2026-07-05T03:13:19.944120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P","json":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P.json","graph_json":"https://pith.science/api/pith-number/3QX237ZV6VG3UV6CQLAUXU2A5P/graph.json","events_json":"https://pith.science/api/pith-number/3QX237ZV6VG3UV6CQLAUXU2A5P/events.json","paper":"https://pith.science/paper/3QX237ZV"},"agent_actions":{"view_html":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P","download_json":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P.json","view_paper":"https://pith.science/paper/3QX237ZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03761&json=true","fetch_graph":"https://pith.science/api/pith-number/3QX237ZV6VG3UV6CQLAUXU2A5P/graph.json","fetch_events":"https://pith.science/api/pith-number/3QX237ZV6VG3UV6CQLAUXU2A5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/action/storage_attestation","attest_author":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/action/author_attestation","sign_citation":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/action/citation_signature","submit_replication":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/action/replication_record"}},"created_at":"2026-07-05T03:13:19.944120+00:00","updated_at":"2026-07-05T03:13:19.944120+00:00"}