{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VZI4VXVQ7PRQMDXSUTZHDD4VUM","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":"c3c319fd23910886b9089c739aeb1114428767cd9f48500bd5f2c826bd828774","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-11T09:51:29Z","title_canon_sha256":"6a054efba35b336f7ca64827a51fd36d59e560384b437dcf2091a73d6886e406"},"schema_version":"1.0","source":{"id":"2106.06279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06279","created_at":"2026-07-05T02:48:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06279v1","created_at":"2026-07-05T02:48:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06279","created_at":"2026-07-05T02:48:28Z"},{"alias_kind":"pith_short_12","alias_value":"VZI4VXVQ7PRQ","created_at":"2026-07-05T02:48:28Z"},{"alias_kind":"pith_short_16","alias_value":"VZI4VXVQ7PRQMDXS","created_at":"2026-07-05T02:48:28Z"},{"alias_kind":"pith_short_8","alias_value":"VZI4VXVQ","created_at":"2026-07-05T02:48:28Z"}],"graph_snapshots":[{"event_id":"sha256:29075c2650cf1dbb0050300839d26483740a4ccb100dd6dda33d7ae0372dcf5b","target":"graph","created_at":"2026-07-05T02:48:28Z","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/2106.06279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play. Precisely, we focus on two-player, zero-sum, episodic, tabular IIG under the perfect-recall assumption where the only feedback is realizations of the game (bandit feedback). In particular, the dynamic of the IIG is not known -- we can only access it by sampling or interacting with a game simulator. For this learning setting, we provide the Implicit Exploration Online Mirror Descent (IXOMD) algorithm. It is a model-free algorithm with a high-probability bound on the convergence rat","authors_text":"Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-11T09:51:29Z","title":"Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06279","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":"sha256:880981e4a77577d66e4ddb853ef9072662701a6dfb7f8295def5f324605bd82a","target":"record","created_at":"2026-07-05T02:48:28Z","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":"c3c319fd23910886b9089c739aeb1114428767cd9f48500bd5f2c826bd828774","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-11T09:51:29Z","title_canon_sha256":"6a054efba35b336f7ca64827a51fd36d59e560384b437dcf2091a73d6886e406"},"schema_version":"1.0","source":{"id":"2106.06279","kind":"arxiv","version":1}},"canonical_sha256":"ae51cadeb0fbe3060ef2a4f2718f95a33813bd267fbc83cf3a3313751697dbea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae51cadeb0fbe3060ef2a4f2718f95a33813bd267fbc83cf3a3313751697dbea","first_computed_at":"2026-07-05T02:48:28.334353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:28.334353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"euoSSFdKk9JAOlxZB1+MroNGPOhD2hARaGbQsta9qnauUMJS4e7zKL44F9tql7jHd+OhEz1AdUPmPmBLmbwFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:28.334833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:880981e4a77577d66e4ddb853ef9072662701a6dfb7f8295def5f324605bd82a","sha256:29075c2650cf1dbb0050300839d26483740a4ccb100dd6dda33d7ae0372dcf5b"],"state_sha256":"31c0ee9852797387c4b7aad7592d2ae897d64633c0fa7760dd3511b333a871be"}