{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ECPDOJ236MFLCPVSDUDRO5TDET","short_pith_number":"pith:ECPDOJ23","schema_version":"1.0","canonical_sha256":"209e37275bf30ab13eb21d0717766324e6707e24c02605ae83696d4f37006ccd","source":{"kind":"arxiv","id":"2409.16450","version":2},"attestation_state":"computed","paper":{"title":"A Multi-Agent Multi-Environment Mixed Q-Learning for Partially Decentralized Wireless Network Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Talha Bozkus, Urbashi Mitra","submitted_at":"2024-09-24T20:34:47Z","abstract_excerpt":"Q-learning is a powerful tool for network control and policy optimization in wireless networks, but it struggles with large state spaces. Recent advancements, like multi-environment mixed Q-learning (MEMQ), improves performance and reduces complexity by integrating multiple Q-learning algorithms across multiple related environments so-called digital cousins. However, MEMQ is designed for centralized single-agent networks and is not suitable for decentralized or multi-agent networks. To address this challenge, we propose a novel multi-agent MEMQ algorithm for partially decentralized wireless ne"},"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":"2409.16450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2024-09-24T20:34:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"681e7c34e7c41902a2a2f7e9a436edb43bdc0f57dd456d2cfa1762472f575694","abstract_canon_sha256":"e981e529206a7634636976a0f310746aec9b4621449e11080ceaf8639f3c1eca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:12.545594Z","signature_b64":"VLAiENtvX5bj38A9kkz+3BjMrJb4RYePQUkZ+uVn/8wcD80HzGQ7hsoQV+4x8TSZ/5v3XfR+6bxFwqk0GjZhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"209e37275bf30ab13eb21d0717766324e6707e24c02605ae83696d4f37006ccd","last_reissued_at":"2026-07-05T09:55:12.545032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:12.545032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Agent Multi-Environment Mixed Q-Learning for Partially Decentralized Wireless Network Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Talha Bozkus, Urbashi Mitra","submitted_at":"2024-09-24T20:34:47Z","abstract_excerpt":"Q-learning is a powerful tool for network control and policy optimization in wireless networks, but it struggles with large state spaces. Recent advancements, like multi-environment mixed Q-learning (MEMQ), improves performance and reduces complexity by integrating multiple Q-learning algorithms across multiple related environments so-called digital cousins. However, MEMQ is designed for centralized single-agent networks and is not suitable for decentralized or multi-agent networks. To address this challenge, we propose a novel multi-agent MEMQ algorithm for partially decentralized wireless ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16450","kind":"arxiv","version":2},"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/2409.16450/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":"2409.16450","created_at":"2026-07-05T09:55:12.545104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16450v2","created_at":"2026-07-05T09:55:12.545104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16450","created_at":"2026-07-05T09:55:12.545104+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECPDOJ236MFL","created_at":"2026-07-05T09:55:12.545104+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECPDOJ236MFLCPVS","created_at":"2026-07-05T09:55:12.545104+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECPDOJ23","created_at":"2026-07-05T09:55:12.545104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08360","citing_title":"Coverage Analysis for Digital Cousin Selection -- Improving Multi-Environment Q-Learning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET","json":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET.json","graph_json":"https://pith.science/api/pith-number/ECPDOJ236MFLCPVSDUDRO5TDET/graph.json","events_json":"https://pith.science/api/pith-number/ECPDOJ236MFLCPVSDUDRO5TDET/events.json","paper":"https://pith.science/paper/ECPDOJ23"},"agent_actions":{"view_html":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET","download_json":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET.json","view_paper":"https://pith.science/paper/ECPDOJ23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16450&json=true","fetch_graph":"https://pith.science/api/pith-number/ECPDOJ236MFLCPVSDUDRO5TDET/graph.json","fetch_events":"https://pith.science/api/pith-number/ECPDOJ236MFLCPVSDUDRO5TDET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET/action/storage_attestation","attest_author":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET/action/author_attestation","sign_citation":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET/action/citation_signature","submit_replication":"https://pith.science/pith/ECPDOJ236MFLCPVSDUDRO5TDET/action/replication_record"}},"created_at":"2026-07-05T09:55:12.545104+00:00","updated_at":"2026-07-05T09:55:12.545104+00:00"}