{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DYUI2ZU4M5NF4TLSIFBXULSNIN","short_pith_number":"pith:DYUI2ZU4","schema_version":"1.0","canonical_sha256":"1e288d669c675a5e4d7241437a2e4d43508c5a54efe87cd615bd77a2a7844ad8","source":{"kind":"arxiv","id":"1909.10651","version":1},"attestation_state":"computed","paper":{"title":"Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Jiachen Yang, Zhi Zhang","submitted_at":"2019-09-23T23:39:00Z","abstract_excerpt":"Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions. Recent studies applying deep reinforcement learning (RL) to optimize single traffic lights have shown significant improvement over conventional control. However, optimization of global traffic condition over a large road network fundamentally is a cooperative multi-agent control problem, for which single-agent RL is not suitable due to environment non-stationarity and infeasibility of optimizing over an exponential joint-action space. Moti"},"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":"1909.10651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T23:39:00Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"813b3881e315f081a145775ea4209af174f032b3c4281e88c0792e432eaba5cc","abstract_canon_sha256":"be52e02fc53c0e761561b9b0b875352ff27505a1c2750f3b01570938584a0c38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:41.474104Z","signature_b64":"5HSfetQywZIOQf3EMA4E9OxuHgtffcU6E6EF9e3nQYGgMxao2KlhVeCMeE+HKDpwuCpR1pQUnUYaSnzFOnGPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e288d669c675a5e4d7241437a2e4d43508c5a54efe87cd615bd77a2a7844ad8","last_reissued_at":"2026-07-05T00:24:41.473619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:41.473619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Jiachen Yang, Zhi Zhang","submitted_at":"2019-09-23T23:39:00Z","abstract_excerpt":"Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions. Recent studies applying deep reinforcement learning (RL) to optimize single traffic lights have shown significant improvement over conventional control. However, optimization of global traffic condition over a large road network fundamentally is a cooperative multi-agent control problem, for which single-agent RL is not suitable due to environment non-stationarity and infeasibility of optimizing over an exponential joint-action space. Moti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10651","kind":"arxiv","version":1},"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/1909.10651/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":"1909.10651","created_at":"2026-07-05T00:24:41.473682+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.10651v1","created_at":"2026-07-05T00:24:41.473682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10651","created_at":"2026-07-05T00:24:41.473682+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYUI2ZU4M5NF","created_at":"2026-07-05T00:24:41.473682+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYUI2ZU4M5NF4TLS","created_at":"2026-07-05T00:24:41.473682+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYUI2ZU4","created_at":"2026-07-05T00:24:41.473682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24992","citing_title":"Scaling up Energy-Aware Multi-Agent Reinforcement Learning for Mission-Oriented Drone Networks with Individual Reward","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN","json":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN.json","graph_json":"https://pith.science/api/pith-number/DYUI2ZU4M5NF4TLSIFBXULSNIN/graph.json","events_json":"https://pith.science/api/pith-number/DYUI2ZU4M5NF4TLSIFBXULSNIN/events.json","paper":"https://pith.science/paper/DYUI2ZU4"},"agent_actions":{"view_html":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN","download_json":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN.json","view_paper":"https://pith.science/paper/DYUI2ZU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.10651&json=true","fetch_graph":"https://pith.science/api/pith-number/DYUI2ZU4M5NF4TLSIFBXULSNIN/graph.json","fetch_events":"https://pith.science/api/pith-number/DYUI2ZU4M5NF4TLSIFBXULSNIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN/action/storage_attestation","attest_author":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN/action/author_attestation","sign_citation":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN/action/citation_signature","submit_replication":"https://pith.science/pith/DYUI2ZU4M5NF4TLSIFBXULSNIN/action/replication_record"}},"created_at":"2026-07-05T00:24:41.473682+00:00","updated_at":"2026-07-05T00:24:41.473682+00:00"}