{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FPOF5FUJVGZ2BOTJPAIEXS73EV","short_pith_number":"pith:FPOF5FUJ","schema_version":"1.0","canonical_sha256":"2bdc5e9689a9b3a0ba6978104bcbfb25719358c76918fe73b13ec161c42b85fc","source":{"kind":"arxiv","id":"2206.04044","version":2},"attestation_state":"computed","paper":{"title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Gen Li, Jianqing Fan, Yuling Yan, Yuxin Chen","submitted_at":"2022-06-08T17:58:06Z","abstract_excerpt":"This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov games from offline data. Specifically, consider a $\\gamma$-discounted infinite-horizon Markov game with $S$ states, where the max-player has $A$ actions and the min-player has $B$ actions. We propose a pessimistic model-based algorithm with Bernstein-style lower confidence bounds -- called VI-LCB-Game -- that provably finds an $\\varepsilon$-approximate Nash equilibrium with a sample complexity no larger than $\\frac{C_{\\mathsf{clipped}}^{\\star}S(A+B)}{(1-\\gamma)^{3}\\varepsilon^{2}}$ (up to some log factor)."},"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":"2206.04044","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T17:58:06Z","cross_cats_sorted":["cs.GT","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"24978ce42b5a102902afc1142974520643a8e33b0eb9bea36daf30ff5fefffcd","abstract_canon_sha256":"30a9c1138450eaddc1a29620c1478337fca8ab2c081d6d4cca77236fa881da22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:38.046244Z","signature_b64":"+Wbhtxkwe4ffq82/V4RAF+lH/BubnPYisos+d6i1gufuUXE4FnpkQb6MSbopfc9nfvGMa5K2jA7MV6NI7fdNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bdc5e9689a9b3a0ba6978104bcbfb25719358c76918fe73b13ec161c42b85fc","last_reissued_at":"2026-07-05T10:31:38.045692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:38.045692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Gen Li, Jianqing Fan, Yuling Yan, Yuxin Chen","submitted_at":"2022-06-08T17:58:06Z","abstract_excerpt":"This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov games from offline data. Specifically, consider a $\\gamma$-discounted infinite-horizon Markov game with $S$ states, where the max-player has $A$ actions and the min-player has $B$ actions. We propose a pessimistic model-based algorithm with Bernstein-style lower confidence bounds -- called VI-LCB-Game -- that provably finds an $\\varepsilon$-approximate Nash equilibrium with a sample complexity no larger than $\\frac{C_{\\mathsf{clipped}}^{\\star}S(A+B)}{(1-\\gamma)^{3}\\varepsilon^{2}}$ (up to some log factor)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04044","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/2206.04044/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":"2206.04044","created_at":"2026-07-05T10:31:38.045752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04044v2","created_at":"2026-07-05T10:31:38.045752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04044","created_at":"2026-07-05T10:31:38.045752+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPOF5FUJVGZ2","created_at":"2026-07-05T10:31:38.045752+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPOF5FUJVGZ2BOTJ","created_at":"2026-07-05T10:31:38.045752+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPOF5FUJ","created_at":"2026-07-05T10:31:38.045752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":165,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03393","citing_title":"Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity","ref_index":238,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV","json":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV.json","graph_json":"https://pith.science/api/pith-number/FPOF5FUJVGZ2BOTJPAIEXS73EV/graph.json","events_json":"https://pith.science/api/pith-number/FPOF5FUJVGZ2BOTJPAIEXS73EV/events.json","paper":"https://pith.science/paper/FPOF5FUJ"},"agent_actions":{"view_html":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV","download_json":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV.json","view_paper":"https://pith.science/paper/FPOF5FUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04044&json=true","fetch_graph":"https://pith.science/api/pith-number/FPOF5FUJVGZ2BOTJPAIEXS73EV/graph.json","fetch_events":"https://pith.science/api/pith-number/FPOF5FUJVGZ2BOTJPAIEXS73EV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/action/storage_attestation","attest_author":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/action/author_attestation","sign_citation":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/action/citation_signature","submit_replication":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/action/replication_record"}},"created_at":"2026-07-05T10:31:38.045752+00:00","updated_at":"2026-07-05T10:31:38.045752+00:00"}