{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K5AELOP2FERTBM5KWAAAVY6XWT","short_pith_number":"pith:K5AELOP2","schema_version":"1.0","canonical_sha256":"574045b9fa292330b3aab0000ae3d7b4c51392af6f3321fcb6326d269f2fd6b8","source":{"kind":"arxiv","id":"2309.00656","version":1},"attestation_state":"computed","paper":{"title":"Local and adaptive mirror descents in extensive-form games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.GT","authors_text":"C\\^ome Fiegel, Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Vianney Perchet","submitted_at":"2023-09-01T09:20:49Z","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 "},"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":"2309.00656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2023-09-01T09:20:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b6fa2fb69192976ebae6a33fcc69d21bbeda3c0fc4962f278e33dcbc8827d158","abstract_canon_sha256":"39e746de6008f65c7b4c3a8450f8ff50d0b540d63acb3c2c179a323899412e53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:03.485175Z","signature_b64":"sksLeykH7A65ODNG35Kv4ggai1q6UEAXAQ78gVjs5HN+wuijQeU03q8aIVsnxwa4jg9N9xUN1gsCqr5CuxevBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"574045b9fa292330b3aab0000ae3d7b4c51392af6f3321fcb6326d269f2fd6b8","last_reissued_at":"2026-07-05T06:47:03.484689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:03.484689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local and adaptive mirror descents in extensive-form games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.GT","authors_text":"C\\^ome Fiegel, Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Vianney Perchet","submitted_at":"2023-09-01T09:20:49Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00656","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/2309.00656/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":"2309.00656","created_at":"2026-07-05T06:47:03.484752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00656v1","created_at":"2026-07-05T06:47:03.484752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00656","created_at":"2026-07-05T06:47:03.484752+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5AELOP2FERT","created_at":"2026-07-05T06:47:03.484752+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5AELOP2FERTBM5K","created_at":"2026-07-05T06:47:03.484752+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5AELOP2","created_at":"2026-07-05T06:47:03.484752+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/K5AELOP2FERTBM5KWAAAVY6XWT","json":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT.json","graph_json":"https://pith.science/api/pith-number/K5AELOP2FERTBM5KWAAAVY6XWT/graph.json","events_json":"https://pith.science/api/pith-number/K5AELOP2FERTBM5KWAAAVY6XWT/events.json","paper":"https://pith.science/paper/K5AELOP2"},"agent_actions":{"view_html":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT","download_json":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT.json","view_paper":"https://pith.science/paper/K5AELOP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00656&json=true","fetch_graph":"https://pith.science/api/pith-number/K5AELOP2FERTBM5KWAAAVY6XWT/graph.json","fetch_events":"https://pith.science/api/pith-number/K5AELOP2FERTBM5KWAAAVY6XWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT/action/storage_attestation","attest_author":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT/action/author_attestation","sign_citation":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT/action/citation_signature","submit_replication":"https://pith.science/pith/K5AELOP2FERTBM5KWAAAVY6XWT/action/replication_record"}},"created_at":"2026-07-05T06:47:03.484752+00:00","updated_at":"2026-07-05T06:47:03.484752+00:00"}