{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JTCPQJSMN67RCTAHHMJW3AYMWV","short_pith_number":"pith:JTCPQJSM","schema_version":"1.0","canonical_sha256":"4cc4f8264c6fbf114c073b136d830cb5570dd26c55bd71fc1f217118d2a01163","source":{"kind":"arxiv","id":"1903.12348","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Traffic Control with Adaptive Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Guang Lin, Tehuan Chen, Wentao Chen","submitted_at":"2019-03-29T03:52:23Z","abstract_excerpt":"This paper proposes a reinforcement learning approach for traffic control with the adaptive horizon. To build the controller for the traffic network, a Q-learning-based strategy that controls the green light passing time at the network intersections is applied. The controller includes two components: the regular Q-learning controller that controls the traffic light signal, and the adaptive controller that continuously optimizes the action space for the Q-learning algorithm in order to improve the efficiency of the Q-learning algorithm. The regular Q-learning controller uses the control cost fu"},"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":"1903.12348","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2019-03-29T03:52:23Z","cross_cats_sorted":[],"title_canon_sha256":"c8087423797ae23153e78a9225ddb7951cd1c8f5616f2cfaa38aaae725ce0cbf","abstract_canon_sha256":"c328b9828338fcc3e145776e82aa54acedc290dd13dcab9767b5bf034af54679"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:54.284692Z","signature_b64":"SPKYXitoQNnPhzdzibaRocnq0YmcrSjxSrGI8RaaedVDF0lvsfTDJHHR+1E2juEHxdH72CQ07wcbBEM8fXCeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cc4f8264c6fbf114c073b136d830cb5570dd26c55bd71fc1f217118d2a01163","last_reissued_at":"2026-05-17T23:49:54.284219Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:54.284219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Traffic Control with Adaptive Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Guang Lin, Tehuan Chen, Wentao Chen","submitted_at":"2019-03-29T03:52:23Z","abstract_excerpt":"This paper proposes a reinforcement learning approach for traffic control with the adaptive horizon. To build the controller for the traffic network, a Q-learning-based strategy that controls the green light passing time at the network intersections is applied. The controller includes two components: the regular Q-learning controller that controls the traffic light signal, and the adaptive controller that continuously optimizes the action space for the Q-learning algorithm in order to improve the efficiency of the Q-learning algorithm. The regular Q-learning controller uses the control cost fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12348","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":"1903.12348","created_at":"2026-05-17T23:49:54.284282+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.12348v1","created_at":"2026-05-17T23:49:54.284282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12348","created_at":"2026-05-17T23:49:54.284282+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTCPQJSMN67R","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTCPQJSMN67RCTAH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTCPQJSM","created_at":"2026-05-18T12:33:21.387695+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/JTCPQJSMN67RCTAHHMJW3AYMWV","json":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV.json","graph_json":"https://pith.science/api/pith-number/JTCPQJSMN67RCTAHHMJW3AYMWV/graph.json","events_json":"https://pith.science/api/pith-number/JTCPQJSMN67RCTAHHMJW3AYMWV/events.json","paper":"https://pith.science/paper/JTCPQJSM"},"agent_actions":{"view_html":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV","download_json":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV.json","view_paper":"https://pith.science/paper/JTCPQJSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.12348&json=true","fetch_graph":"https://pith.science/api/pith-number/JTCPQJSMN67RCTAHHMJW3AYMWV/graph.json","fetch_events":"https://pith.science/api/pith-number/JTCPQJSMN67RCTAHHMJW3AYMWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV/action/storage_attestation","attest_author":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV/action/author_attestation","sign_citation":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV/action/citation_signature","submit_replication":"https://pith.science/pith/JTCPQJSMN67RCTAHHMJW3AYMWV/action/replication_record"}},"created_at":"2026-05-17T23:49:54.284282+00:00","updated_at":"2026-05-17T23:49:54.284282+00:00"}