{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JOJCZ3K5ZPQSMLY2NTAI3332O6","short_pith_number":"pith:JOJCZ3K5","schema_version":"1.0","canonical_sha256":"4b922ced5dcbe1262f1a6cc08def7a77ac9a1abf38abcfa0d56ca06b1f9f7064","source":{"kind":"arxiv","id":"2108.02731","version":2},"attestation_state":"computed","paper":{"title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Haotian Gu, Renyuan Xu, Xiaoli Wei, Xin Guo","submitted_at":"2021-08-05T16:52:36Z","abstract_excerpt":"One of the challenges for multi-agent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. While exciting progress has been made to analyze decentralized MARL with the network of agents for social networks and team video games, little is known theoretically for decentralized MARL with the network of states for modeling self-driving vehicles, ride-sharing, and data and traffic routing.\n  This paper proposes a framework of localized training and decentralized execution to stud"},"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":"2108.02731","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-05T16:52:36Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"fc1a0df9fd1b16ff1c9e3c3979b03e21f701d74315f100097fd319c83b9e4ccf","abstract_canon_sha256":"78f3dd53ed3a2988b1eab25991930060b3b1b68283cc553e3820a3a957464868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:16.908834Z","signature_b64":"Nvd9h0SYxHsIDN0QVjMYGaXZvJTd77cAg8iD+7ksVmuueMbbFfz3nav7tA+w7/udUOxWc44KVP2n/rbPnMedAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b922ced5dcbe1262f1a6cc08def7a77ac9a1abf38abcfa0d56ca06b1f9f7064","last_reissued_at":"2026-07-05T03:58:16.908366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:16.908366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Haotian Gu, Renyuan Xu, Xiaoli Wei, Xin Guo","submitted_at":"2021-08-05T16:52:36Z","abstract_excerpt":"One of the challenges for multi-agent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. While exciting progress has been made to analyze decentralized MARL with the network of agents for social networks and team video games, little is known theoretically for decentralized MARL with the network of states for modeling self-driving vehicles, ride-sharing, and data and traffic routing.\n  This paper proposes a framework of localized training and decentralized execution to stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02731","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/2108.02731/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":"2108.02731","created_at":"2026-07-05T03:58:16.908425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02731v2","created_at":"2026-07-05T03:58:16.908425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02731","created_at":"2026-07-05T03:58:16.908425+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOJCZ3K5ZPQS","created_at":"2026-07-05T03:58:16.908425+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOJCZ3K5ZPQSMLY2","created_at":"2026-07-05T03:58:16.908425+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOJCZ3K5","created_at":"2026-07-05T03:58:16.908425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10142","citing_title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6","json":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6.json","graph_json":"https://pith.science/api/pith-number/JOJCZ3K5ZPQSMLY2NTAI3332O6/graph.json","events_json":"https://pith.science/api/pith-number/JOJCZ3K5ZPQSMLY2NTAI3332O6/events.json","paper":"https://pith.science/paper/JOJCZ3K5"},"agent_actions":{"view_html":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6","download_json":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6.json","view_paper":"https://pith.science/paper/JOJCZ3K5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02731&json=true","fetch_graph":"https://pith.science/api/pith-number/JOJCZ3K5ZPQSMLY2NTAI3332O6/graph.json","fetch_events":"https://pith.science/api/pith-number/JOJCZ3K5ZPQSMLY2NTAI3332O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6/action/storage_attestation","attest_author":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6/action/author_attestation","sign_citation":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6/action/citation_signature","submit_replication":"https://pith.science/pith/JOJCZ3K5ZPQSMLY2NTAI3332O6/action/replication_record"}},"created_at":"2026-07-05T03:58:16.908425+00:00","updated_at":"2026-07-05T03:58:16.908425+00:00"}