{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OIG5YGP4RB7UITD4DZ7MM2MTD5","short_pith_number":"pith:OIG5YGP4","schema_version":"1.0","canonical_sha256":"720ddc19fc887f444c7c1e7ec669931f41af290db44ca2da13ea114523a81f78","source":{"kind":"arxiv","id":"2107.13632","version":1},"attestation_state":"computed","paper":{"title":"Efficient Episodic Learning of Nonstationary and Unknown Zero-Sum Games Using Expert Game Ensembles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.GT","authors_text":"Quanyan Zhu, Yunian Pan","submitted_at":"2021-07-28T20:35:12Z","abstract_excerpt":"Game theory provides essential analysis in many applications of strategic interactions. However, the question of how to construct a game model and what is its fidelity is seldom addressed. In this work, we consider learning in a class of repeated zero-sum games with unknown, time-varying payoff matrix, and noisy feedbacks, by making use of an ensemble of benchmark game models. These models can be pre-trained and collected dynamically during sequential plays. They serve as prior side information and imperfectly underpin the unknown true game model. We propose OFULinMat, an episodic learning alg"},"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":"2107.13632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.GT","submitted_at":"2021-07-28T20:35:12Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"1b5f560d10528b1e8d4d5c482417bf4ad1e4f211804dc32cc2b4872308514221","abstract_canon_sha256":"0b0a1deb67419f44d0f0aa8867f800f860027170241bcff881b36d5d6ee1ec4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:38.585155Z","signature_b64":"5CaIa5Ho4fDmShORWTdLnjGws33DkDw6BvPNj9CIhl6UwXlxWn57gMeAs6MKidNMeW9SYqWo/E4XAEbJB6YoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"720ddc19fc887f444c7c1e7ec669931f41af290db44ca2da13ea114523a81f78","last_reissued_at":"2026-07-05T03:01:38.584720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:38.584720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Episodic Learning of Nonstationary and Unknown Zero-Sum Games Using Expert Game Ensembles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.GT","authors_text":"Quanyan Zhu, Yunian Pan","submitted_at":"2021-07-28T20:35:12Z","abstract_excerpt":"Game theory provides essential analysis in many applications of strategic interactions. However, the question of how to construct a game model and what is its fidelity is seldom addressed. In this work, we consider learning in a class of repeated zero-sum games with unknown, time-varying payoff matrix, and noisy feedbacks, by making use of an ensemble of benchmark game models. These models can be pre-trained and collected dynamically during sequential plays. They serve as prior side information and imperfectly underpin the unknown true game model. We propose OFULinMat, an episodic learning alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13632","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/2107.13632/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":"2107.13632","created_at":"2026-07-05T03:01:38.584784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13632v1","created_at":"2026-07-05T03:01:38.584784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13632","created_at":"2026-07-05T03:01:38.584784+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIG5YGP4RB7U","created_at":"2026-07-05T03:01:38.584784+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIG5YGP4RB7UITD4","created_at":"2026-07-05T03:01:38.584784+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIG5YGP4","created_at":"2026-07-05T03:01:38.584784+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/OIG5YGP4RB7UITD4DZ7MM2MTD5","json":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5.json","graph_json":"https://pith.science/api/pith-number/OIG5YGP4RB7UITD4DZ7MM2MTD5/graph.json","events_json":"https://pith.science/api/pith-number/OIG5YGP4RB7UITD4DZ7MM2MTD5/events.json","paper":"https://pith.science/paper/OIG5YGP4"},"agent_actions":{"view_html":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5","download_json":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5.json","view_paper":"https://pith.science/paper/OIG5YGP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13632&json=true","fetch_graph":"https://pith.science/api/pith-number/OIG5YGP4RB7UITD4DZ7MM2MTD5/graph.json","fetch_events":"https://pith.science/api/pith-number/OIG5YGP4RB7UITD4DZ7MM2MTD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5/action/storage_attestation","attest_author":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5/action/author_attestation","sign_citation":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5/action/citation_signature","submit_replication":"https://pith.science/pith/OIG5YGP4RB7UITD4DZ7MM2MTD5/action/replication_record"}},"created_at":"2026-07-05T03:01:38.584784+00:00","updated_at":"2026-07-05T03:01:38.584784+00:00"}