{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6NOZBDGEWVD5FL26ZGY37R5PKV","short_pith_number":"pith:6NOZBDGE","schema_version":"1.0","canonical_sha256":"f35d908cc4b547d2af5ec9b1bfc7af5573ca532d3b4f399a61e0baab1c3e64d3","source":{"kind":"arxiv","id":"1903.04527","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jie Wang, Lara Codec\\`a, TianShu Chu, Zhaojian Li","submitted_at":"2019-03-11T18:28:58Z","abstract_excerpt":"Reinforcement learning (RL) is a promising data-driven approach for adaptive traffic signal control (ATSC) in complex urban traffic networks, and deep neural networks further enhance its learning power. However, centralized RL is infeasible for large-scale ATSC due to the extremely high dimension of the joint action space. Multi-agent RL (MARL) overcomes the scalability issue by distributing the global control to each local RL agent, but it introduces new challenges: now the environment becomes partially observable from the viewpoint of each local agent due to limited communication among agent"},"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":"1903.04527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-11T18:28:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3e396095e2cb23f348f4573474aef8166894e4016f23be23b8ea07a58f701d3a","abstract_canon_sha256":"eb775735c6d862c026a791a367efb60d9592d40a5890bda326cd96517b3b5752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:29.378788Z","signature_b64":"BhMnvLm40Et/Id5lz8gIw3/Xq39wm5CkNWKlFXPX9eMyCXwZbvt+9nhDSzIy2uzd/yrdYHnO3+lzFNS9pjMRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35d908cc4b547d2af5ec9b1bfc7af5573ca532d3b4f399a61e0baab1c3e64d3","last_reissued_at":"2026-05-17T23:51:29.378394Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:29.378394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jie Wang, Lara Codec\\`a, TianShu Chu, Zhaojian Li","submitted_at":"2019-03-11T18:28:58Z","abstract_excerpt":"Reinforcement learning (RL) is a promising data-driven approach for adaptive traffic signal control (ATSC) in complex urban traffic networks, and deep neural networks further enhance its learning power. However, centralized RL is infeasible for large-scale ATSC due to the extremely high dimension of the joint action space. Multi-agent RL (MARL) overcomes the scalability issue by distributing the global control to each local RL agent, but it introduces new challenges: now the environment becomes partially observable from the viewpoint of each local agent due to limited communication among agent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04527","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":""},"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":"1903.04527","created_at":"2026-05-17T23:51:29.378446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.04527v1","created_at":"2026-05-17T23:51:29.378446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04527","created_at":"2026-05-17T23:51:29.378446+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NOZBDGEWVD5","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NOZBDGEWVD5FL26","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NOZBDGE","created_at":"2026-05-18T12:33:10.108867+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/6NOZBDGEWVD5FL26ZGY37R5PKV","json":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV.json","graph_json":"https://pith.science/api/pith-number/6NOZBDGEWVD5FL26ZGY37R5PKV/graph.json","events_json":"https://pith.science/api/pith-number/6NOZBDGEWVD5FL26ZGY37R5PKV/events.json","paper":"https://pith.science/paper/6NOZBDGE"},"agent_actions":{"view_html":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV","download_json":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV.json","view_paper":"https://pith.science/paper/6NOZBDGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.04527&json=true","fetch_graph":"https://pith.science/api/pith-number/6NOZBDGEWVD5FL26ZGY37R5PKV/graph.json","fetch_events":"https://pith.science/api/pith-number/6NOZBDGEWVD5FL26ZGY37R5PKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV/action/storage_attestation","attest_author":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV/action/author_attestation","sign_citation":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV/action/citation_signature","submit_replication":"https://pith.science/pith/6NOZBDGEWVD5FL26ZGY37R5PKV/action/replication_record"}},"created_at":"2026-05-17T23:51:29.378446+00:00","updated_at":"2026-05-17T23:51:29.378446+00:00"}