{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SAXN4JWGC7MIWRMQ4KGYUKQGDR","short_pith_number":"pith:SAXN4JWG","canonical_record":{"source":{"id":"2209.12430","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T05:35:44Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"8cf318351b723edc4fa06a508f35437e98db32486a5383f18ea45834fce4dcc1","abstract_canon_sha256":"fe93145a86104b5a401e4290f9cabfd1e96b569fb881afd9c9835157fe558546"},"schema_version":"1.0"},"canonical_sha256":"902ede26c617d88b4590e28d8a2a061c6fb313cb193025b8f78f1afc7587dd1f","source":{"kind":"arxiv","id":"2209.12430","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12430","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12430v2","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12430","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"pith_short_12","alias_value":"SAXN4JWGC7MI","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"pith_short_16","alias_value":"SAXN4JWGC7MIWRMQ","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"pith_short_8","alias_value":"SAXN4JWG","created_at":"2026-07-05T05:40:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SAXN4JWGC7MIWRMQ4KGYUKQGDR","target":"record","payload":{"canonical_record":{"source":{"id":"2209.12430","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T05:35:44Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"8cf318351b723edc4fa06a508f35437e98db32486a5383f18ea45834fce4dcc1","abstract_canon_sha256":"fe93145a86104b5a401e4290f9cabfd1e96b569fb881afd9c9835157fe558546"},"schema_version":"1.0"},"canonical_sha256":"902ede26c617d88b4590e28d8a2a061c6fb313cb193025b8f78f1afc7587dd1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:08.843394Z","signature_b64":"+QhIKIgT/9imHMY6orTBRdqpYjATcAFWKTpGhFFrLyubs7O1MiDAZs9QJX+fhjuprD0MfBDKYJ6DKbUZyXhKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"902ede26c617d88b4590e28d8a2a061c6fb313cb193025b8f78f1afc7587dd1f","last_reissued_at":"2026-07-05T05:40:08.842983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:08.842983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.12430","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":"2026-07-05T05:40:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/LtylwUqWrxrKlrouORrC4OpQIo2ojSsboHkxLfIuCRIYdOjLcS51oqtVcE0zoMeDwWCGBg1hhQWdiWBNzWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:12:36.669095Z"},"content_sha256":"d374123541b8190895ddc492f3e6b697246ac462b7d751e926ad0447d7afcbc5","schema_version":"1.0","event_id":"sha256:d374123541b8190895ddc492f3e6b697246ac462b7d751e926ad0447d7afcbc5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SAXN4JWGC7MIWRMQ4KGYUKQGDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Cong Ma, Yuepeng Yang","submitted_at":"2022-09-26T05:35:44Z","abstract_excerpt":"We prove that optimistic-follow-the-regularized-leader (OFTRL), together with smooth value updates, finds an $O(T^{-1})$-approximate Nash equilibrium in $T$ iterations for two-player zero-sum Markov games with full information. This improves the $\\tilde{O}(T^{-5/6})$ convergence rate recently shown in the paper Zhang et al (2022). The refined analysis hinges on two essential ingredients. First, the sum of the regrets of the two players, though not necessarily non-negative as in normal-form games, is approximately non-negative in Markov games. This property allows us to bound the second-order p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12430","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/2209.12430/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":"2026-07-05T05:40:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2n/e08LGIyEPR3aCbOivL0AwOiq1ATRQNs8BhHtaF8q33vcZOzMmByYhwanMJM5gHOpRX9/BHxuCxuMqjzeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:12:36.669810Z"},"content_sha256":"73afd973fe67a79c004897b3c8b708cd951e9c2e89f9b6b2ab7428fc434df092","schema_version":"1.0","event_id":"sha256:73afd973fe67a79c004897b3c8b708cd951e9c2e89f9b6b2ab7428fc434df092"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR/bundle.json","state_url":"https://pith.science/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR/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":"2026-08-12T19:12:36Z","links":{"resolver":"https://pith.science/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR","bundle":"https://pith.science/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR/bundle.json","state":"https://pith.science/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SAXN4JWGC7MIWRMQ4KGYUKQGDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SAXN4JWGC7MIWRMQ4KGYUKQGDR","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":"fe93145a86104b5a401e4290f9cabfd1e96b569fb881afd9c9835157fe558546","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T05:35:44Z","title_canon_sha256":"8cf318351b723edc4fa06a508f35437e98db32486a5383f18ea45834fce4dcc1"},"schema_version":"1.0","source":{"id":"2209.12430","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12430","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12430v2","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12430","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"pith_short_12","alias_value":"SAXN4JWGC7MI","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"pith_short_16","alias_value":"SAXN4JWGC7MIWRMQ","created_at":"2026-07-05T05:40:08Z"},{"alias_kind":"pith_short_8","alias_value":"SAXN4JWG","created_at":"2026-07-05T05:40:08Z"}],"graph_snapshots":[{"event_id":"sha256:73afd973fe67a79c004897b3c8b708cd951e9c2e89f9b6b2ab7428fc434df092","target":"graph","created_at":"2026-07-05T05:40:08Z","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/2209.12430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We prove that optimistic-follow-the-regularized-leader (OFTRL), together with smooth value updates, finds an $O(T^{-1})$-approximate Nash equilibrium in $T$ iterations for two-player zero-sum Markov games with full information. This improves the $\\tilde{O}(T^{-5/6})$ convergence rate recently shown in the paper Zhang et al (2022). The refined analysis hinges on two essential ingredients. First, the sum of the regrets of the two players, though not necessarily non-negative as in normal-form games, is approximately non-negative in Markov games. This property allows us to bound the second-order p","authors_text":"Cong Ma, Yuepeng Yang","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T05:35:44Z","title":"$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12430","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:d374123541b8190895ddc492f3e6b697246ac462b7d751e926ad0447d7afcbc5","target":"record","created_at":"2026-07-05T05:40:08Z","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":"fe93145a86104b5a401e4290f9cabfd1e96b569fb881afd9c9835157fe558546","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T05:35:44Z","title_canon_sha256":"8cf318351b723edc4fa06a508f35437e98db32486a5383f18ea45834fce4dcc1"},"schema_version":"1.0","source":{"id":"2209.12430","kind":"arxiv","version":2}},"canonical_sha256":"902ede26c617d88b4590e28d8a2a061c6fb313cb193025b8f78f1afc7587dd1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"902ede26c617d88b4590e28d8a2a061c6fb313cb193025b8f78f1afc7587dd1f","first_computed_at":"2026-07-05T05:40:08.842983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:08.842983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+QhIKIgT/9imHMY6orTBRdqpYjATcAFWKTpGhFFrLyubs7O1MiDAZs9QJX+fhjuprD0MfBDKYJ6DKbUZyXhKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:08.843394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.12430","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d374123541b8190895ddc492f3e6b697246ac462b7d751e926ad0447d7afcbc5","sha256:73afd973fe67a79c004897b3c8b708cd951e9c2e89f9b6b2ab7428fc434df092"],"state_sha256":"c5407156404f2f49f5b3fa6c84290062d884bcc48fc80576d68a379235916c82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4rRR+Br+8nlK8bX92I7Z57yqBpkFODebKJtCEe71MyFoVjcn4WnXvyLItaKPjgWhc/aDsiCjOycr9MF4opd6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:12:36.674417Z","bundle_sha256":"e406b8f8978090bcb9a7b0336ae99fd4cf84124e3414296acde191392c182b5d"}}