{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K5AELOP2FERTBM5KWAAAVY6XWT","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":"39e746de6008f65c7b4c3a8450f8ff50d0b540d63acb3c2c179a323899412e53","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2023-09-01T09:20:49Z","title_canon_sha256":"b6fa2fb69192976ebae6a33fcc69d21bbeda3c0fc4962f278e33dcbc8827d158"},"schema_version":"1.0","source":{"id":"2309.00656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00656","created_at":"2026-07-05T06:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00656v1","created_at":"2026-07-05T06:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00656","created_at":"2026-07-05T06:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"K5AELOP2FERT","created_at":"2026-07-05T06:47:03Z"},{"alias_kind":"pith_short_16","alias_value":"K5AELOP2FERTBM5K","created_at":"2026-07-05T06:47:03Z"},{"alias_kind":"pith_short_8","alias_value":"K5AELOP2","created_at":"2026-07-05T06:47:03Z"}],"graph_snapshots":[{"event_id":"sha256:29334733ca1a96174aa6afcf9639e132b571657b555f9248decef363fe88ec3d","target":"graph","created_at":"2026-07-05T06:47:03Z","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/2309.00656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study how to learn $\\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback. In this setting, players update their policies sequentially based on their observations over a fixed number of episodes, denoted by $T$. Existing procedures suffer from high variance due to the use of importance sampling over sequences of actions (Steinberger et al., 2020; McAleer et al., 2022). To reduce this variance, we consider a fixed sampling approach, where players still update their policies over time, but with observations obtained through a given fixed sampling ","authors_text":"C\\^ome Fiegel, Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Vianney Perchet","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2023-09-01T09:20:49Z","title":"Local and adaptive mirror descents in extensive-form games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00656","kind":"arxiv","version":1},"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":"sha256:345a74b1414df3af46158f017299d05cca9bf7ef271a95d9b01c60aa74007862","target":"record","created_at":"2026-07-05T06:47:03Z","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":"39e746de6008f65c7b4c3a8450f8ff50d0b540d63acb3c2c179a323899412e53","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2023-09-01T09:20:49Z","title_canon_sha256":"b6fa2fb69192976ebae6a33fcc69d21bbeda3c0fc4962f278e33dcbc8827d158"},"schema_version":"1.0","source":{"id":"2309.00656","kind":"arxiv","version":1}},"canonical_sha256":"574045b9fa292330b3aab0000ae3d7b4c51392af6f3321fcb6326d269f2fd6b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"574045b9fa292330b3aab0000ae3d7b4c51392af6f3321fcb6326d269f2fd6b8","first_computed_at":"2026-07-05T06:47:03.484689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:03.484689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sksLeykH7A65ODNG35Kv4ggai1q6UEAXAQ78gVjs5HN+wuijQeU03q8aIVsnxwa4jg9N9xUN1gsCqr5CuxevBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:03.485175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:345a74b1414df3af46158f017299d05cca9bf7ef271a95d9b01c60aa74007862","sha256:29334733ca1a96174aa6afcf9639e132b571657b555f9248decef363fe88ec3d"],"state_sha256":"7297af81c2395da620d41161dfc64d902a4e5781737bc19a3fce80d3f78ca129"}