{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:74GFFGYFQXPVWIBYHSARMWMYC5","short_pith_number":"pith:74GFFGYF","schema_version":"1.0","canonical_sha256":"ff0c529b0585df5b20383c81165998174655413eb6c5bb970d187cfa9b2cc5f7","source":{"kind":"arxiv","id":"2503.18201","version":1},"attestation_state":"computed","paper":{"title":"Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arash Sarmadi, Georg Ziegner, Hung Mac Chan Le, Michael Choi, Sahil Sakhuja","submitted_at":"2025-03-23T20:52:21Z","abstract_excerpt":"Multi-echelon inventory optimization (MEIO) is critical for effective supply chain management, but its inherent complexity can pose significant challenges. Heuristics are commonly used to address this complexity, yet they often face limitations in scope and scalability. Recent research has found deep reinforcement learning (DRL) to be a promising alternative to traditional heuristics, offering greater versatility by utilizing dynamic decision-making capabilities. However, since DRL is known to struggle with the curse of dimensionality, its relevance to complex real-life supply chain scenarios "},"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":"2503.18201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-23T20:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"5050edb186ccc4c43a2a55b1eed283577a477ce5abddcd19da3d84be5facb48c","abstract_canon_sha256":"df738c1d9558c1ab20f1e5e35142f604f7e983015bf1c897ca8b5437deca32ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:04.947290Z","signature_b64":"4DoRLtl4wNy/8m9WtoydTvL6LVIdaaDqeJqzQr6+GO08cFhFvzTZP4bJfbBpetDALIUBwvpRMMZ9jclRByEeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff0c529b0585df5b20383c81165998174655413eb6c5bb970d187cfa9b2cc5f7","last_reissued_at":"2026-07-05T10:38:04.946635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:04.946635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arash Sarmadi, Georg Ziegner, Hung Mac Chan Le, Michael Choi, Sahil Sakhuja","submitted_at":"2025-03-23T20:52:21Z","abstract_excerpt":"Multi-echelon inventory optimization (MEIO) is critical for effective supply chain management, but its inherent complexity can pose significant challenges. Heuristics are commonly used to address this complexity, yet they often face limitations in scope and scalability. Recent research has found deep reinforcement learning (DRL) to be a promising alternative to traditional heuristics, offering greater versatility by utilizing dynamic decision-making capabilities. However, since DRL is known to struggle with the curse of dimensionality, its relevance to complex real-life supply chain scenarios "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18201","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/2503.18201/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":"2503.18201","created_at":"2026-07-05T10:38:04.946716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18201v1","created_at":"2026-07-05T10:38:04.946716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18201","created_at":"2026-07-05T10:38:04.946716+00:00"},{"alias_kind":"pith_short_12","alias_value":"74GFFGYFQXPV","created_at":"2026-07-05T10:38:04.946716+00:00"},{"alias_kind":"pith_short_16","alias_value":"74GFFGYFQXPVWIBY","created_at":"2026-07-05T10:38:04.946716+00:00"},{"alias_kind":"pith_short_8","alias_value":"74GFFGYF","created_at":"2026-07-05T10:38:04.946716+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/74GFFGYFQXPVWIBYHSARMWMYC5","json":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5.json","graph_json":"https://pith.science/api/pith-number/74GFFGYFQXPVWIBYHSARMWMYC5/graph.json","events_json":"https://pith.science/api/pith-number/74GFFGYFQXPVWIBYHSARMWMYC5/events.json","paper":"https://pith.science/paper/74GFFGYF"},"agent_actions":{"view_html":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5","download_json":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5.json","view_paper":"https://pith.science/paper/74GFFGYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18201&json=true","fetch_graph":"https://pith.science/api/pith-number/74GFFGYFQXPVWIBYHSARMWMYC5/graph.json","fetch_events":"https://pith.science/api/pith-number/74GFFGYFQXPVWIBYHSARMWMYC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5/action/storage_attestation","attest_author":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5/action/author_attestation","sign_citation":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5/action/citation_signature","submit_replication":"https://pith.science/pith/74GFFGYFQXPVWIBYHSARMWMYC5/action/replication_record"}},"created_at":"2026-07-05T10:38:04.946716+00:00","updated_at":"2026-07-05T10:38:04.946716+00:00"}