{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YC6K2Q5HPZ7HJE24GQ7DONOTYT","short_pith_number":"pith:YC6K2Q5H","schema_version":"1.0","canonical_sha256":"c0bcad43a77e7e74935c343e3735d3c4eb290780e9d75c0857ad608a82865164","source":{"kind":"arxiv","id":"2006.01482","version":4},"attestation_state":"computed","paper":{"title":"Multi-Agent Determinantal Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"David Mguni, Jun Wang, Kun Shao, Liheng Chen, Weinan Zhang, Yaodong Yang, Ying Wen","submitted_at":"2020-06-02T09:32:48Z","abstract_excerpt":"Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, an extension of determinantal point process (DPP) with partition-matroid constraint to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-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":"2006.01482","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T09:32:48Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"8c2545c89f94cede0a8d9cfea5ca6201ab7a18a9ee70ed862ec4c8fe5d3ac303","abstract_canon_sha256":"f53b927b04d81a60009e0bdd7f98c24be8e2af50774ed23f8586c9f743b232c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:07.174195Z","signature_b64":"ZBE2CPl4Gwc3IykEvcDXKqP+Vw3pv/FRjKtUrjqDT5nyoR2Pse4+3VAJVTb2CA+zfYNUybrtTdXRHuiyJdkLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0bcad43a77e7e74935c343e3735d3c4eb290780e9d75c0857ad608a82865164","last_reissued_at":"2026-07-05T01:09:07.173797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:07.173797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Determinantal Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"David Mguni, Jun Wang, Kun Shao, Liheng Chen, Weinan Zhang, Yaodong Yang, Ying Wen","submitted_at":"2020-06-02T09:32:48Z","abstract_excerpt":"Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, an extension of determinantal point process (DPP) with partition-matroid constraint to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01482","kind":"arxiv","version":4},"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/2006.01482/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":"2006.01482","created_at":"2026-07-05T01:09:07.173854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.01482v4","created_at":"2026-07-05T01:09:07.173854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01482","created_at":"2026-07-05T01:09:07.173854+00:00"},{"alias_kind":"pith_short_12","alias_value":"YC6K2Q5HPZ7H","created_at":"2026-07-05T01:09:07.173854+00:00"},{"alias_kind":"pith_short_16","alias_value":"YC6K2Q5HPZ7HJE24","created_at":"2026-07-05T01:09:07.173854+00:00"},{"alias_kind":"pith_short_8","alias_value":"YC6K2Q5H","created_at":"2026-07-05T01:09:07.173854+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/YC6K2Q5HPZ7HJE24GQ7DONOTYT","json":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT.json","graph_json":"https://pith.science/api/pith-number/YC6K2Q5HPZ7HJE24GQ7DONOTYT/graph.json","events_json":"https://pith.science/api/pith-number/YC6K2Q5HPZ7HJE24GQ7DONOTYT/events.json","paper":"https://pith.science/paper/YC6K2Q5H"},"agent_actions":{"view_html":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT","download_json":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT.json","view_paper":"https://pith.science/paper/YC6K2Q5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.01482&json=true","fetch_graph":"https://pith.science/api/pith-number/YC6K2Q5HPZ7HJE24GQ7DONOTYT/graph.json","fetch_events":"https://pith.science/api/pith-number/YC6K2Q5HPZ7HJE24GQ7DONOTYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT/action/storage_attestation","attest_author":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT/action/author_attestation","sign_citation":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT/action/citation_signature","submit_replication":"https://pith.science/pith/YC6K2Q5HPZ7HJE24GQ7DONOTYT/action/replication_record"}},"created_at":"2026-07-05T01:09:07.173854+00:00","updated_at":"2026-07-05T01:09:07.173854+00:00"}