{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MIWB3TRQ7XJ2VN3AKJ6P7GUPDT","short_pith_number":"pith:MIWB3TRQ","schema_version":"1.0","canonical_sha256":"622c1dce30fdd3aab760527cff9a8f1cff1dde893898dc99dcdfb9f9443fbd6f","source":{"kind":"arxiv","id":"2212.12567","version":2},"attestation_state":"computed","paper":{"title":"Adapting to game trees in zero-sum imperfect information games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"C\\^ome Fiegel, Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Vianney Perchet","submitted_at":"2022-12-23T19:45:25Z","abstract_excerpt":"Imperfect information games (IIG) are games in which each player only partially observes the current game state. We study how to learn $\\epsilon$-optimal strategies in a zero-sum IIG through self-play with trajectory feedback. We give a problem-independent lower bound $\\widetilde{\\mathcal{O}}(H(A_{\\mathcal{X}}+B_{\\mathcal{Y}})/\\epsilon^2)$ on the required number of realizations to learn these strategies with high probability, where $H$ is the length of the game, $A_{\\mathcal{X}}$ and $B_{\\mathcal{Y}}$ are the total number of actions for the two players. We also propose two Follow the Regulariz"},"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":"2212.12567","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T19:45:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7d5af6a0604856005b13185b251e66b1419a5a903dfcfb814b620a13d92f03e0","abstract_canon_sha256":"4db811c85e26b43b6b287123af898affb8988c8eb28ea487bed76479894b5ab6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:02.425790Z","signature_b64":"j9fzaHwmbXtzQ/HHQdoRcLKfCE1pKxWhoP26XJ0XfqEBscMgI3BoLK5FGA2cSAK2s/K2IUdhxynhN+qos+eXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"622c1dce30fdd3aab760527cff9a8f1cff1dde893898dc99dcdfb9f9443fbd6f","last_reissued_at":"2026-07-05T05:42:02.425234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:02.425234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting to game trees in zero-sum imperfect information games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"C\\^ome Fiegel, Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Vianney Perchet","submitted_at":"2022-12-23T19:45:25Z","abstract_excerpt":"Imperfect information games (IIG) are games in which each player only partially observes the current game state. We study how to learn $\\epsilon$-optimal strategies in a zero-sum IIG through self-play with trajectory feedback. We give a problem-independent lower bound $\\widetilde{\\mathcal{O}}(H(A_{\\mathcal{X}}+B_{\\mathcal{Y}})/\\epsilon^2)$ on the required number of realizations to learn these strategies with high probability, where $H$ is the length of the game, $A_{\\mathcal{X}}$ and $B_{\\mathcal{Y}}$ are the total number of actions for the two players. We also propose two Follow the Regulariz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12567","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/2212.12567/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":"2212.12567","created_at":"2026-07-05T05:42:02.425291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.12567v2","created_at":"2026-07-05T05:42:02.425291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12567","created_at":"2026-07-05T05:42:02.425291+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIWB3TRQ7XJ2","created_at":"2026-07-05T05:42:02.425291+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIWB3TRQ7XJ2VN3A","created_at":"2026-07-05T05:42:02.425291+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIWB3TRQ","created_at":"2026-07-05T05:42:02.425291+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/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT","json":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT.json","graph_json":"https://pith.science/api/pith-number/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/graph.json","events_json":"https://pith.science/api/pith-number/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/events.json","paper":"https://pith.science/paper/MIWB3TRQ"},"agent_actions":{"view_html":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT","download_json":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT.json","view_paper":"https://pith.science/paper/MIWB3TRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.12567&json=true","fetch_graph":"https://pith.science/api/pith-number/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/graph.json","fetch_events":"https://pith.science/api/pith-number/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/action/storage_attestation","attest_author":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/action/author_attestation","sign_citation":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/action/citation_signature","submit_replication":"https://pith.science/pith/MIWB3TRQ7XJ2VN3AKJ6P7GUPDT/action/replication_record"}},"created_at":"2026-07-05T05:42:02.425291+00:00","updated_at":"2026-07-05T05:42:02.425291+00:00"}