{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZXXFMGJCWZYPDVNH4YSWJYNPUM","short_pith_number":"pith:ZXXFMGJC","schema_version":"1.0","canonical_sha256":"cdee561922b670f1d5a7e62564e1afa3207d52a3372de1f9d353b539c273eefc","source":{"kind":"arxiv","id":"2301.06889","version":2},"attestation_state":"computed","paper":{"title":"Mean-Field Control based Approximation of Multi-Agent Reinforcement Learning in Presence of a Non-decomposable Shared Global State","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Satish V. Ukkusuri, Vaneet Aggarwal, Washim Uddin Mondal","submitted_at":"2023-01-13T18:55:58Z","abstract_excerpt":"Mean Field Control (MFC) is a powerful approximation tool to solve large-scale Multi-Agent Reinforcement Learning (MARL) problems. However, the success of MFC relies on the presumption that given the local states and actions of all the agents, the next (local) states of the agents evolve conditionally independent of each other. Here we demonstrate that even in a MARL setting where agents share a common global state in addition to their local states evolving conditionally independently (thus introducing a correlation between the state transition processes of individual agents), the MFC can stil"},"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":"2301.06889","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T18:55:58Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"cec5bbea5fa2c9511b34174ae8fddf32fb9fa71af3b4438f348c708e1025bbf3","abstract_canon_sha256":"3abae18c879bdcae2731b54367f8595d0ad49ca5d2257e2f7a1637eaa03a53ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:23.647138Z","signature_b64":"J1LVpM/I/nMv+u1WyJ9A70bowCjdeTYhlpmLODSdG8dpRFBrJ7RJcIoYbTdN0Jg1Cn0UdYsMCFFSkqLCs0fAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdee561922b670f1d5a7e62564e1afa3207d52a3372de1f9d353b539c273eefc","last_reissued_at":"2026-07-05T06:14:23.646675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:23.646675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean-Field Control based Approximation of Multi-Agent Reinforcement Learning in Presence of a Non-decomposable Shared Global State","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Satish V. Ukkusuri, Vaneet Aggarwal, Washim Uddin Mondal","submitted_at":"2023-01-13T18:55:58Z","abstract_excerpt":"Mean Field Control (MFC) is a powerful approximation tool to solve large-scale Multi-Agent Reinforcement Learning (MARL) problems. However, the success of MFC relies on the presumption that given the local states and actions of all the agents, the next (local) states of the agents evolve conditionally independent of each other. Here we demonstrate that even in a MARL setting where agents share a common global state in addition to their local states evolving conditionally independently (thus introducing a correlation between the state transition processes of individual agents), the MFC can stil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06889","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/2301.06889/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":"2301.06889","created_at":"2026-07-05T06:14:23.646734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06889v2","created_at":"2026-07-05T06:14:23.646734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06889","created_at":"2026-07-05T06:14:23.646734+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXXFMGJCWZYP","created_at":"2026-07-05T06:14:23.646734+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXXFMGJCWZYPDVNH","created_at":"2026-07-05T06:14:23.646734+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXXFMGJC","created_at":"2026-07-05T06:14:23.646734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27378","citing_title":"Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM","json":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM.json","graph_json":"https://pith.science/api/pith-number/ZXXFMGJCWZYPDVNH4YSWJYNPUM/graph.json","events_json":"https://pith.science/api/pith-number/ZXXFMGJCWZYPDVNH4YSWJYNPUM/events.json","paper":"https://pith.science/paper/ZXXFMGJC"},"agent_actions":{"view_html":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM","download_json":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM.json","view_paper":"https://pith.science/paper/ZXXFMGJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06889&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXXFMGJCWZYPDVNH4YSWJYNPUM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXXFMGJCWZYPDVNH4YSWJYNPUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM/action/storage_attestation","attest_author":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM/action/author_attestation","sign_citation":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM/action/citation_signature","submit_replication":"https://pith.science/pith/ZXXFMGJCWZYPDVNH4YSWJYNPUM/action/replication_record"}},"created_at":"2026-07-05T06:14:23.646734+00:00","updated_at":"2026-07-05T06:14:23.646734+00:00"}