{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HWOXFQFPAX5SQZJRZ7O36CDWBX","short_pith_number":"pith:HWOXFQFP","schema_version":"1.0","canonical_sha256":"3d9d72c0af05fb286531cfddbf08760dd53384e1a77db16c05ba36b7d1ca8436","source":{"kind":"arxiv","id":"2407.02759","version":1},"attestation_state":"computed","paper":{"title":"Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang Zhou, Chiyu Cheng, Jin Cao, Shaobo Liu, Xingchen Li, Yang Zhao, Yi Zhao","submitted_at":"2024-07-03T02:33:20Z","abstract_excerpt":"This paper explores multi-scenario optimization on large platforms using multi-agent reinforcement learning (MARL). We address this by treating scenarios like search, recommendation, and advertising as a cooperative, partially observable multi-agent decision problem. We introduce the Multi-Agent Recurrent Deterministic Policy Gradient (MARDPG) algorithm, which aligns different scenarios under a shared objective and allows for strategy communication to boost overall performance. Our results show marked improvements in metrics such as click-through rate (CTR), conversion rate, and total sales, c"},"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":"2407.02759","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T02:33:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef85f8032efb55f3d4e0fdc869e5a2845ed170eec9fd6ab0eb8460366d3cd885","abstract_canon_sha256":"e8e979a3e476cf468d7c7ebcef11e2e688126854ed78ade2dbc7be6a43ce8ec3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:41.197979Z","signature_b64":"GEuxqEAJI/fYFcDwB73Z7gwJC7Ok1UMA9rN6rKRjPFarzShftXn5hqohUjgUVXzRsU0lJ01wUbXwqLuRDeShBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d9d72c0af05fb286531cfddbf08760dd53384e1a77db16c05ba36b7d1ca8436","last_reissued_at":"2026-07-05T08:39:41.197595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:41.197595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang Zhou, Chiyu Cheng, Jin Cao, Shaobo Liu, Xingchen Li, Yang Zhao, Yi Zhao","submitted_at":"2024-07-03T02:33:20Z","abstract_excerpt":"This paper explores multi-scenario optimization on large platforms using multi-agent reinforcement learning (MARL). We address this by treating scenarios like search, recommendation, and advertising as a cooperative, partially observable multi-agent decision problem. We introduce the Multi-Agent Recurrent Deterministic Policy Gradient (MARDPG) algorithm, which aligns different scenarios under a shared objective and allows for strategy communication to boost overall performance. Our results show marked improvements in metrics such as click-through rate (CTR), conversion rate, and total sales, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02759","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/2407.02759/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":"2407.02759","created_at":"2026-07-05T08:39:41.197652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02759v1","created_at":"2026-07-05T08:39:41.197652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02759","created_at":"2026-07-05T08:39:41.197652+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWOXFQFPAX5S","created_at":"2026-07-05T08:39:41.197652+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWOXFQFPAX5SQZJR","created_at":"2026-07-05T08:39:41.197652+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWOXFQFP","created_at":"2026-07-05T08:39:41.197652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00068","citing_title":"Dynamic Optimization of Storage Systems Using Reinforcement Learning Techniques","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX","json":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX.json","graph_json":"https://pith.science/api/pith-number/HWOXFQFPAX5SQZJRZ7O36CDWBX/graph.json","events_json":"https://pith.science/api/pith-number/HWOXFQFPAX5SQZJRZ7O36CDWBX/events.json","paper":"https://pith.science/paper/HWOXFQFP"},"agent_actions":{"view_html":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX","download_json":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX.json","view_paper":"https://pith.science/paper/HWOXFQFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02759&json=true","fetch_graph":"https://pith.science/api/pith-number/HWOXFQFPAX5SQZJRZ7O36CDWBX/graph.json","fetch_events":"https://pith.science/api/pith-number/HWOXFQFPAX5SQZJRZ7O36CDWBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX/action/storage_attestation","attest_author":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX/action/author_attestation","sign_citation":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX/action/citation_signature","submit_replication":"https://pith.science/pith/HWOXFQFPAX5SQZJRZ7O36CDWBX/action/replication_record"}},"created_at":"2026-07-05T08:39:41.197652+00:00","updated_at":"2026-07-05T08:39:41.197652+00:00"}