{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TKEFZRT2D3CXIMAR7M6SJTQPEV","short_pith_number":"pith:TKEFZRT2","schema_version":"1.0","canonical_sha256":"9a885cc67a1ec5743011fb3d24ce0f257891a437c45ee019a91e3e7d7b9b2565","source":{"kind":"arxiv","id":"2212.13379","version":1},"attestation_state":"computed","paper":{"title":"Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Pradeep Varakantham, Tanvi Verma","submitted_at":"2022-12-27T06:59:00Z","abstract_excerpt":"In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e.g., aggregation systems such as Uber, Deliveroo). In this paper, we consider such multi-agent systems where each agent is self-interested and takes a sequence of decisions and represent them as a Stochastic Non-atomic Congestion Game (SNCG). We derive key properties for equilibrium solutions in SNCG model with non-atomic and also nearly non-atomic agents. With those key equilibrium properties, we provide a novel Multi-Agent Reinforcement Learning (MARL) mechan"},"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":"2212.13379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2022-12-27T06:59:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdbe47b7ed8622bb0a3a93af418e3ca5c0988cc9f14ff7cc63a01843a912fd42","abstract_canon_sha256":"a32f78bf4caf54d3d1891558e43a2e7a7c77f002c0abc3abb63a0dbc47a7235c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:50.955180Z","signature_b64":"BIHlVJu9mFW+VNxT6QN8l7XBeDJi71pXIkF5uj0cc10ZjQ3Tib+vpXD7RB9maxvFD3Mvxy0e01Pk0hcRZ9ayCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a885cc67a1ec5743011fb3d24ce0f257891a437c45ee019a91e3e7d7b9b2565","last_reissued_at":"2026-07-05T05:28:50.954668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:50.954668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Pradeep Varakantham, Tanvi Verma","submitted_at":"2022-12-27T06:59:00Z","abstract_excerpt":"In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e.g., aggregation systems such as Uber, Deliveroo). In this paper, we consider such multi-agent systems where each agent is self-interested and takes a sequence of decisions and represent them as a Stochastic Non-atomic Congestion Game (SNCG). We derive key properties for equilibrium solutions in SNCG model with non-atomic and also nearly non-atomic agents. With those key equilibrium properties, we provide a novel Multi-Agent Reinforcement Learning (MARL) mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13379","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/2212.13379/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":"2212.13379","created_at":"2026-07-05T05:28:50.954717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13379v1","created_at":"2026-07-05T05:28:50.954717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13379","created_at":"2026-07-05T05:28:50.954717+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKEFZRT2D3CX","created_at":"2026-07-05T05:28:50.954717+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKEFZRT2D3CXIMAR","created_at":"2026-07-05T05:28:50.954717+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKEFZRT2","created_at":"2026-07-05T05:28:50.954717+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/TKEFZRT2D3CXIMAR7M6SJTQPEV","json":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV.json","graph_json":"https://pith.science/api/pith-number/TKEFZRT2D3CXIMAR7M6SJTQPEV/graph.json","events_json":"https://pith.science/api/pith-number/TKEFZRT2D3CXIMAR7M6SJTQPEV/events.json","paper":"https://pith.science/paper/TKEFZRT2"},"agent_actions":{"view_html":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV","download_json":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV.json","view_paper":"https://pith.science/paper/TKEFZRT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13379&json=true","fetch_graph":"https://pith.science/api/pith-number/TKEFZRT2D3CXIMAR7M6SJTQPEV/graph.json","fetch_events":"https://pith.science/api/pith-number/TKEFZRT2D3CXIMAR7M6SJTQPEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV/action/storage_attestation","attest_author":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV/action/author_attestation","sign_citation":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV/action/citation_signature","submit_replication":"https://pith.science/pith/TKEFZRT2D3CXIMAR7M6SJTQPEV/action/replication_record"}},"created_at":"2026-07-05T05:28:50.954717+00:00","updated_at":"2026-07-05T05:28:50.954717+00:00"}