{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5E4AZ6AZFM5ATIOPOCN3EMOS3Y","short_pith_number":"pith:5E4AZ6AZ","schema_version":"1.0","canonical_sha256":"e9380cf8192b3a09a1cf709bb231d2de0c3df4826148d85c9c853fcf1ab70e47","source":{"kind":"arxiv","id":"2402.07082","version":2},"attestation_state":"computed","paper":{"title":"Refined Sample Complexity for Markov Games with Independent Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiwen Cui, Simon S. Du, Yan Dai","submitted_at":"2024-02-11T01:51:15Z","abstract_excerpt":"Markov Games (MG) is an important model for Multi-Agent Reinforcement Learning (MARL). It was long believed that the \"curse of multi-agents\" (i.e., the algorithmic performance drops exponentially with the number of agents) is unavoidable until several recent works (Daskalakis et al., 2023; Cui et al., 2023; Wang et al., 2023). While these works resolved the curse of multi-agents, when the state spaces are prohibitively large and (linear) function approximations are deployed, they either had a slower convergence rate of $O(T^{-1/4})$ or brought a polynomial dependency on the number of actions $"},"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":"2402.07082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T01:51:15Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"b2ee2abdc8c9f272c4f75b57b4516d8d971623b7c5d4013de364c6852b678d33","abstract_canon_sha256":"5d7f0f7e84ef96033a5e7549b2760acd8158f02ae90dec030ca8c7209ff5cc26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:08.415454Z","signature_b64":"i6rNSTYgveJB4lUvKN3sNK7EkAsxW+LX/esHPXQXGKqQhYukCAB4u+/NSmlbGNU5q1AYUfBIXORjQF3/hOPdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9380cf8192b3a09a1cf709bb231d2de0c3df4826148d85c9c853fcf1ab70e47","last_reissued_at":"2026-07-05T08:30:08.414943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:08.414943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refined Sample Complexity for Markov Games with Independent Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiwen Cui, Simon S. Du, Yan Dai","submitted_at":"2024-02-11T01:51:15Z","abstract_excerpt":"Markov Games (MG) is an important model for Multi-Agent Reinforcement Learning (MARL). It was long believed that the \"curse of multi-agents\" (i.e., the algorithmic performance drops exponentially with the number of agents) is unavoidable until several recent works (Daskalakis et al., 2023; Cui et al., 2023; Wang et al., 2023). While these works resolved the curse of multi-agents, when the state spaces are prohibitively large and (linear) function approximations are deployed, they either had a slower convergence rate of $O(T^{-1/4})$ or brought a polynomial dependency on the number of actions $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07082","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/2402.07082/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":"2402.07082","created_at":"2026-07-05T08:30:08.415005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07082v2","created_at":"2026-07-05T08:30:08.415005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07082","created_at":"2026-07-05T08:30:08.415005+00:00"},{"alias_kind":"pith_short_12","alias_value":"5E4AZ6AZFM5A","created_at":"2026-07-05T08:30:08.415005+00:00"},{"alias_kind":"pith_short_16","alias_value":"5E4AZ6AZFM5ATIOP","created_at":"2026-07-05T08:30:08.415005+00:00"},{"alias_kind":"pith_short_8","alias_value":"5E4AZ6AZ","created_at":"2026-07-05T08:30:08.415005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03125","citing_title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y","json":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y.json","graph_json":"https://pith.science/api/pith-number/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/graph.json","events_json":"https://pith.science/api/pith-number/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/events.json","paper":"https://pith.science/paper/5E4AZ6AZ"},"agent_actions":{"view_html":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y","download_json":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y.json","view_paper":"https://pith.science/paper/5E4AZ6AZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07082&json=true","fetch_graph":"https://pith.science/api/pith-number/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/action/storage_attestation","attest_author":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/action/author_attestation","sign_citation":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/action/citation_signature","submit_replication":"https://pith.science/pith/5E4AZ6AZFM5ATIOPOCN3EMOS3Y/action/replication_record"}},"created_at":"2026-07-05T08:30:08.415005+00:00","updated_at":"2026-07-05T08:30:08.415005+00:00"}