{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FPOF5FUJVGZ2BOTJPAIEXS73EV","short_pith_number":"pith:FPOF5FUJ","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"},"canonical_sha256":"2bdc5e9689a9b3a0ba6978104bcbfb25719358c76918fe73b13ec161c42b85fc","source":{"kind":"arxiv","id":"2206.04044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04044","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04044v2","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04044","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"FPOF5FUJVGZ2","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"FPOF5FUJVGZ2BOTJ","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"FPOF5FUJ","created_at":"2026-07-05T10:31:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FPOF5FUJVGZ2BOTJPAIEXS73EV","target":"record","payload":{"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"},"canonical_sha256":"2bdc5e9689a9b3a0ba6978104bcbfb25719358c76918fe73b13ec161c42b85fc","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"},"source_kind":"arxiv","source_id":"2206.04044","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dzg10PK2zpQ6YCVJCVogSI12KiUWhab5KG58Qx1XXEuPh1pFfW4JADlF/lPHeorOMEK8jk+bxKkww+e95SJ6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:27:57.898136Z"},"content_sha256":"9a9370a25212b049e6b2390fd5360c90d42492032b9629e1bbd521a62d07a1ac","schema_version":"1.0","event_id":"sha256:9a9370a25212b049e6b2390fd5360c90d42492032b9629e1bbd521a62d07a1ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FPOF5FUJVGZ2BOTJPAIEXS73EV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"On62V6yKutUwOkkEm4ykpn8Nj4KRcKNkV5iJi7evL6LFkEfLIC7rcmXN9sn8ZLfb5KNwdcO/DNpN00JU1PU6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:27:57.898750Z"},"content_sha256":"6dd4ae8229b7355b66834ec44381dfba0491ca7b89553c3e436a5d0eae869713","schema_version":"1.0","event_id":"sha256:6dd4ae8229b7355b66834ec44381dfba0491ca7b89553c3e436a5d0eae869713"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/bundle.json","state_url":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T16:27:57Z","links":{"resolver":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV","bundle":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/bundle.json","state":"https://pith.science/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPOF5FUJVGZ2BOTJPAIEXS73EV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FPOF5FUJVGZ2BOTJPAIEXS73EV","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":"30a9c1138450eaddc1a29620c1478337fca8ab2c081d6d4cca77236fa881da22","cross_cats_sorted":["cs.GT","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T17:58:06Z","title_canon_sha256":"24978ce42b5a102902afc1142974520643a8e33b0eb9bea36daf30ff5fefffcd"},"schema_version":"1.0","source":{"id":"2206.04044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04044","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04044v2","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04044","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"FPOF5FUJVGZ2","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"FPOF5FUJVGZ2BOTJ","created_at":"2026-07-05T10:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"FPOF5FUJ","created_at":"2026-07-05T10:31:38Z"}],"graph_snapshots":[{"event_id":"sha256:6dd4ae8229b7355b66834ec44381dfba0491ca7b89553c3e436a5d0eae869713","target":"graph","created_at":"2026-07-05T10:31:38Z","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/2206.04044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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).","authors_text":"Gen Li, Jianqing Fan, Yuling Yan, Yuxin Chen","cross_cats":["cs.GT","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T17:58:06Z","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04044","kind":"arxiv","version":2},"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":"sha256:9a9370a25212b049e6b2390fd5360c90d42492032b9629e1bbd521a62d07a1ac","target":"record","created_at":"2026-07-05T10:31:38Z","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":"30a9c1138450eaddc1a29620c1478337fca8ab2c081d6d4cca77236fa881da22","cross_cats_sorted":["cs.GT","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T17:58:06Z","title_canon_sha256":"24978ce42b5a102902afc1142974520643a8e33b0eb9bea36daf30ff5fefffcd"},"schema_version":"1.0","source":{"id":"2206.04044","kind":"arxiv","version":2}},"canonical_sha256":"2bdc5e9689a9b3a0ba6978104bcbfb25719358c76918fe73b13ec161c42b85fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bdc5e9689a9b3a0ba6978104bcbfb25719358c76918fe73b13ec161c42b85fc","first_computed_at":"2026-07-05T10:31:38.045692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:38.045692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Wbhtxkwe4ffq82/V4RAF+lH/BubnPYisos+d6i1gufuUXE4FnpkQb6MSbopfc9nfvGMa5K2jA7MV6NI7fdNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:38.046244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a9370a25212b049e6b2390fd5360c90d42492032b9629e1bbd521a62d07a1ac","sha256:6dd4ae8229b7355b66834ec44381dfba0491ca7b89553c3e436a5d0eae869713"],"state_sha256":"f90248908884fc34701a6b46a2248940a71112239b665cf5240aefb207871536"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YRIa+MM8Vz5nSAYvkxaltelNIp5YsHGMfjzS/sus1lPr2zHpTjPWqwuuPBLDHZKyqsBmmu32ntGVp/+MpFRlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T16:27:57.903080Z","bundle_sha256":"f90541cee1e1fb3f73ae26da2936b72e14d916fd944525d95a9f2d4ef4c41d55"}}