{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VZI4VXVQ7PRQMDXSUTZHDD4VUM","short_pith_number":"pith:VZI4VXVQ","schema_version":"1.0","canonical_sha256":"ae51cadeb0fbe3060ef2a4f2718f95a33813bd267fbc83cf3a3313751697dbea","source":{"kind":"arxiv","id":"2106.06279","version":1},"attestation_state":"computed","paper":{"title":"Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno","submitted_at":"2021-06-11T09:51:29Z","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"},"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":"2106.06279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-11T09:51:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a054efba35b336f7ca64827a51fd36d59e560384b437dcf2091a73d6886e406","abstract_canon_sha256":"c3c319fd23910886b9089c739aeb1114428767cd9f48500bd5f2c826bd828774"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:28.334833Z","signature_b64":"euoSSFdKk9JAOlxZB1+MroNGPOhD2hARaGbQsta9qnauUMJS4e7zKL44F9tql7jHd+OhEz1AdUPmPmBLmbwFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae51cadeb0fbe3060ef2a4f2718f95a33813bd267fbc83cf3a3313751697dbea","last_reissued_at":"2026-07-05T02:48:28.334353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:28.334353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michal Valko, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno","submitted_at":"2021-06-11T09:51:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06279","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/2106.06279/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":"2106.06279","created_at":"2026-07-05T02:48:28.334411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06279v1","created_at":"2026-07-05T02:48:28.334411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06279","created_at":"2026-07-05T02:48:28.334411+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZI4VXVQ7PRQ","created_at":"2026-07-05T02:48:28.334411+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZI4VXVQ7PRQMDXS","created_at":"2026-07-05T02:48:28.334411+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZI4VXVQ","created_at":"2026-07-05T02:48:28.334411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05266","citing_title":"Differential Privacy in the Extensive-Form Bandit Problem","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM","json":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM.json","graph_json":"https://pith.science/api/pith-number/VZI4VXVQ7PRQMDXSUTZHDD4VUM/graph.json","events_json":"https://pith.science/api/pith-number/VZI4VXVQ7PRQMDXSUTZHDD4VUM/events.json","paper":"https://pith.science/paper/VZI4VXVQ"},"agent_actions":{"view_html":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM","download_json":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM.json","view_paper":"https://pith.science/paper/VZI4VXVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06279&json=true","fetch_graph":"https://pith.science/api/pith-number/VZI4VXVQ7PRQMDXSUTZHDD4VUM/graph.json","fetch_events":"https://pith.science/api/pith-number/VZI4VXVQ7PRQMDXSUTZHDD4VUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM/action/storage_attestation","attest_author":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM/action/author_attestation","sign_citation":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM/action/citation_signature","submit_replication":"https://pith.science/pith/VZI4VXVQ7PRQMDXSUTZHDD4VUM/action/replication_record"}},"created_at":"2026-07-05T02:48:28.334411+00:00","updated_at":"2026-07-05T02:48:28.334411+00:00"}