{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q74FXGJ6JGKTQWSDL4IP4MOXTR","short_pith_number":"pith:Q74FXGJ6","schema_version":"1.0","canonical_sha256":"87f85b993e4995385a435f10fe31d79c4e8dfa6ef8f55736e1c506a39da8a0cb","source":{"kind":"arxiv","id":"2112.07859","version":2},"attestation_state":"computed","paper":{"title":"Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"John R. Birge, Qianqian Ma, Tamer Ba\\c{s}ar, Zuguang Gao","submitted_at":"2021-12-15T03:33:39Z","abstract_excerpt":"Learning in stochastic games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in stochastic games in the non-asymptotic regime. In particular, we establish the finite-sample complexity of fully decentralized Q-learning algorithms in a significant class of general-sum stochastic games (SGs) - weakly acyclic SGs, which includes the common cooperative MARL setting with an identical reward to all agents (a Markov team problem) as a special case. We focus on the practical while challenging setting of 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":"2112.07859","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2021-12-15T03:33:39Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"7ed88e226585c7117eb5c9503671a19a663613a76fffd7d6b33fdb7387958fb9","abstract_canon_sha256":"fcdea76ebe6292aca0c089e3008868db3adbd69451f72e9ef93e2473713cc905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:28.670943Z","signature_b64":"8k6zdKFxp8mJcwRzrpxKXABFzozKaQOkjL3vDZZhNNKAC4NxkiH9EkmTz7XbKgyh4UAq6Mf0FElzppVdoPi+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87f85b993e4995385a435f10fe31d79c4e8dfa6ef8f55736e1c506a39da8a0cb","last_reissued_at":"2026-07-05T03:41:28.670464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:28.670464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"John R. Birge, Qianqian Ma, Tamer Ba\\c{s}ar, Zuguang Gao","submitted_at":"2021-12-15T03:33:39Z","abstract_excerpt":"Learning in stochastic games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in stochastic games in the non-asymptotic regime. In particular, we establish the finite-sample complexity of fully decentralized Q-learning algorithms in a significant class of general-sum stochastic games (SGs) - weakly acyclic SGs, which includes the common cooperative MARL setting with an identical reward to all agents (a Markov team problem) as a special case. We focus on the practical while challenging setting of fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07859","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/2112.07859/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":"2112.07859","created_at":"2026-07-05T03:41:28.670523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07859v2","created_at":"2026-07-05T03:41:28.670523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07859","created_at":"2026-07-05T03:41:28.670523+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q74FXGJ6JGKT","created_at":"2026-07-05T03:41:28.670523+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q74FXGJ6JGKTQWSD","created_at":"2026-07-05T03:41:28.670523+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q74FXGJ6","created_at":"2026-07-05T03:41:28.670523+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/Q74FXGJ6JGKTQWSDL4IP4MOXTR","json":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR.json","graph_json":"https://pith.science/api/pith-number/Q74FXGJ6JGKTQWSDL4IP4MOXTR/graph.json","events_json":"https://pith.science/api/pith-number/Q74FXGJ6JGKTQWSDL4IP4MOXTR/events.json","paper":"https://pith.science/paper/Q74FXGJ6"},"agent_actions":{"view_html":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR","download_json":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR.json","view_paper":"https://pith.science/paper/Q74FXGJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07859&json=true","fetch_graph":"https://pith.science/api/pith-number/Q74FXGJ6JGKTQWSDL4IP4MOXTR/graph.json","fetch_events":"https://pith.science/api/pith-number/Q74FXGJ6JGKTQWSDL4IP4MOXTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR/action/storage_attestation","attest_author":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR/action/author_attestation","sign_citation":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR/action/citation_signature","submit_replication":"https://pith.science/pith/Q74FXGJ6JGKTQWSDL4IP4MOXTR/action/replication_record"}},"created_at":"2026-07-05T03:41:28.670523+00:00","updated_at":"2026-07-05T03:41:28.670523+00:00"}