{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GMDTLLTYDQGEQ5W2EB6Y5JKF6U","short_pith_number":"pith:GMDTLLTY","schema_version":"1.0","canonical_sha256":"330735ae781c0c4876da207d8ea545f523e726be85741a29dabe151e4d7c6db6","source":{"kind":"arxiv","id":"1712.07305","version":1},"attestation_state":"computed","paper":{"title":"Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Xin, Fangchen Liu, Xiangyu Kong, Yizhou Wang","submitted_at":"2017-12-20T03:00:46Z","abstract_excerpt":"Many tasks in artificial intelligence require the collaboration of multiple agents. We exam deep reinforcement learning for multi-agent domains. Recent research efforts often take the form of two seemingly conflicting perspectives, the decentralized perspective, where each agent is supposed to have its own controller; and the centralized perspective, where one assumes there is a larger model controlling all agents. In this regard, we revisit the idea of the master-slave architecture by incorporating both perspectives within one framework. Such a hierarchical structure naturally leverages advan"},"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":"1712.07305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-20T03:00:46Z","cross_cats_sorted":[],"title_canon_sha256":"1d443853e809901e0ce6c15fb00a5ad082c4d5f7f623f27eead9743f685410ff","abstract_canon_sha256":"6cec5833ad5e4560ec57995dedad087bb7593be6dc093fa18196dd82cfb3edc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:34.866457Z","signature_b64":"u1bcz/g9S3yVd4z1P6PRQIq3Yo6r2SGCWeIcM800LjYZR/9CbtUysOpYLd4mBR8ffD+MqBYhcrK9sXh5OKBaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"330735ae781c0c4876da207d8ea545f523e726be85741a29dabe151e4d7c6db6","last_reissued_at":"2026-05-18T00:27:34.865747Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:34.865747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Xin, Fangchen Liu, Xiangyu Kong, Yizhou Wang","submitted_at":"2017-12-20T03:00:46Z","abstract_excerpt":"Many tasks in artificial intelligence require the collaboration of multiple agents. We exam deep reinforcement learning for multi-agent domains. Recent research efforts often take the form of two seemingly conflicting perspectives, the decentralized perspective, where each agent is supposed to have its own controller; and the centralized perspective, where one assumes there is a larger model controlling all agents. In this regard, we revisit the idea of the master-slave architecture by incorporating both perspectives within one framework. Such a hierarchical structure naturally leverages advan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07305","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":"1712.07305","created_at":"2026-05-18T00:27:34.865889+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.07305v1","created_at":"2026-05-18T00:27:34.865889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07305","created_at":"2026-05-18T00:27:34.865889+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMDTLLTYDQGE","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMDTLLTYDQGEQ5W2","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMDTLLTY","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.21223","citing_title":"Obstacle-aware navigation of smart microswimmers in a turbulent flow","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U","json":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U.json","graph_json":"https://pith.science/api/pith-number/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/graph.json","events_json":"https://pith.science/api/pith-number/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/events.json","paper":"https://pith.science/paper/GMDTLLTY"},"agent_actions":{"view_html":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U","download_json":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U.json","view_paper":"https://pith.science/paper/GMDTLLTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.07305&json=true","fetch_graph":"https://pith.science/api/pith-number/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/graph.json","fetch_events":"https://pith.science/api/pith-number/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/action/storage_attestation","attest_author":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/action/author_attestation","sign_citation":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/action/citation_signature","submit_replication":"https://pith.science/pith/GMDTLLTYDQGEQ5W2EB6Y5JKF6U/action/replication_record"}},"created_at":"2026-05-18T00:27:34.865889+00:00","updated_at":"2026-05-18T00:27:34.865889+00:00"}