{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MIWB3TRQ7XJ2VN3AKJ6P7GUPDT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4db811c85e26b43b6b287123af898affb8988c8eb28ea487bed76479894b5ab6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T19:45:25Z","title_canon_sha256":"7d5af6a0604856005b13185b251e66b1419a5a903dfcfb814b620a13d92f03e0"},"schema_version":"1.0","source":{"id":"2212.12567","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12567","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12567v2","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12567","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_12","alias_value":"MIWB3TRQ7XJ2","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_16","alias_value":"MIWB3TRQ7XJ2VN3A","created_at":"2026-07-05T05:42:02Z"},{"alias_kind":"pith_short_8","alias_value":"MIWB3TRQ","created_at":"2026-07-05T05:42:02Z"}],"graph_snapshots":[{"event_id":"sha256:e47ea9d75a82badbdb7804e62ab69417ff6d5ba03c0485702c5da002f5e93fe3","target":"graph","created_at":"2026-07-05T05:42:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.12567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"C\\^ome Fiegel, Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Vianney Perchet","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T19:45:25Z","title":"Adapting to game trees in zero-sum imperfect information games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12567","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8d5e29cb7bdc75edd33ef4c0e1bd8edaafd0edcc517f9c005594204d80379e3d","target":"record","created_at":"2026-07-05T05:42:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4db811c85e26b43b6b287123af898affb8988c8eb28ea487bed76479894b5ab6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T19:45:25Z","title_canon_sha256":"7d5af6a0604856005b13185b251e66b1419a5a903dfcfb814b620a13d92f03e0"},"schema_version":"1.0","source":{"id":"2212.12567","kind":"arxiv","version":2}},"canonical_sha256":"622c1dce30fdd3aab760527cff9a8f1cff1dde893898dc99dcdfb9f9443fbd6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"622c1dce30fdd3aab760527cff9a8f1cff1dde893898dc99dcdfb9f9443fbd6f","first_computed_at":"2026-07-05T05:42:02.425234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:02.425234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j9fzaHwmbXtzQ/HHQdoRcLKfCE1pKxWhoP26XJ0XfqEBscMgI3BoLK5FGA2cSAK2s/K2IUdhxynhN+qos+eXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:02.425790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.12567","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d5e29cb7bdc75edd33ef4c0e1bd8edaafd0edcc517f9c005594204d80379e3d","sha256:e47ea9d75a82badbdb7804e62ab69417ff6d5ba03c0485702c5da002f5e93fe3"],"state_sha256":"42f8d9b8bbca6ee487368e2f6d0b90c055c7cbb93bc2f92c0ca453ec73676f27"}