{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NIBGPROUIXIU5PXOHC4QZN77BB","short_pith_number":"pith:NIBGPROU","schema_version":"1.0","canonical_sha256":"6a0267c5d445d14ebeee38b90cb7ff087673d3f9a66cb72115d7ca53e19188d5","source":{"kind":"arxiv","id":"2201.03522","version":2},"attestation_state":"computed","paper":{"title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiwen Cui, Simon S. Du","submitted_at":"2022-01-10T18:34:32Z","abstract_excerpt":"We study what dataset assumption permits solving offline two-player zero-sum Markov games. In stark contrast to the offline single-agent Markov decision process, we show that the single strategy concentration assumption is insufficient for learning the Nash equilibrium (NE) strategy in offline two-player zero-sum Markov games. On the other hand, we propose a new assumption named unilateral concentration and design a pessimism-type algorithm that is provably efficient under this assumption. In addition, we show that the unilateral concentration assumption is necessary for learning an NE strateg"},"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":"2201.03522","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T18:34:32Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"d515c71ac6a05805a8b4f4b02cca301feaf1e3e26aeacf4a9d2c2df41798a686","abstract_canon_sha256":"237f68da8be2712d4537792335d0bc1d70e8969b7b523319ba40590d7498cde6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:29.278948Z","signature_b64":"uUochQa0KZk4sIhr9BN0aWz9XIWNVs+goo5tRk6GmMe+lATL1AgjtAjZQW2z0SdhdbMkJKYgEcSksv8szLy9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a0267c5d445d14ebeee38b90cb7ff087673d3f9a66cb72115d7ca53e19188d5","last_reissued_at":"2026-07-05T05:06:29.278519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:29.278519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiwen Cui, Simon S. Du","submitted_at":"2022-01-10T18:34:32Z","abstract_excerpt":"We study what dataset assumption permits solving offline two-player zero-sum Markov games. In stark contrast to the offline single-agent Markov decision process, we show that the single strategy concentration assumption is insufficient for learning the Nash equilibrium (NE) strategy in offline two-player zero-sum Markov games. On the other hand, we propose a new assumption named unilateral concentration and design a pessimism-type algorithm that is provably efficient under this assumption. In addition, we show that the unilateral concentration assumption is necessary for learning an NE strateg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03522","kind":"arxiv","version":2},"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/2201.03522/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":"2201.03522","created_at":"2026-07-05T05:06:29.278574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03522v2","created_at":"2026-07-05T05:06:29.278574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03522","created_at":"2026-07-05T05:06:29.278574+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIBGPROUIXIU","created_at":"2026-07-05T05:06:29.278574+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIBGPROUIXIU5PXO","created_at":"2026-07-05T05:06:29.278574+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIBGPROU","created_at":"2026-07-05T05:06:29.278574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17189","citing_title":"Sample-efficient inductive matrix completion with noise and inexact side-information","ref_index":164,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB","json":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB.json","graph_json":"https://pith.science/api/pith-number/NIBGPROUIXIU5PXOHC4QZN77BB/graph.json","events_json":"https://pith.science/api/pith-number/NIBGPROUIXIU5PXOHC4QZN77BB/events.json","paper":"https://pith.science/paper/NIBGPROU"},"agent_actions":{"view_html":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB","download_json":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB.json","view_paper":"https://pith.science/paper/NIBGPROU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03522&json=true","fetch_graph":"https://pith.science/api/pith-number/NIBGPROUIXIU5PXOHC4QZN77BB/graph.json","fetch_events":"https://pith.science/api/pith-number/NIBGPROUIXIU5PXOHC4QZN77BB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB/action/storage_attestation","attest_author":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB/action/author_attestation","sign_citation":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB/action/citation_signature","submit_replication":"https://pith.science/pith/NIBGPROUIXIU5PXOHC4QZN77BB/action/replication_record"}},"created_at":"2026-07-05T05:06:29.278574+00:00","updated_at":"2026-07-05T05:06:29.278574+00:00"}