{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FXSWNDEHOH23UEGSYLFWIXHBNV","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":"4990f7d94aae90a767e6c57cb74935c0bbf99934dd9184471d7ca1b3e2a7d0f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T12:23:24Z","title_canon_sha256":"5f668df3418e6c36abfd1909ef7949baab9f3d5ed242ebbda248cfd396c7fb3c"},"schema_version":"1.0","source":{"id":"2401.17780","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17780","created_at":"2026-07-05T08:38:36Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17780v3","created_at":"2026-07-05T08:38:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17780","created_at":"2026-07-05T08:38:36Z"},{"alias_kind":"pith_short_12","alias_value":"FXSWNDEHOH23","created_at":"2026-07-05T08:38:36Z"},{"alias_kind":"pith_short_16","alias_value":"FXSWNDEHOH23UEGS","created_at":"2026-07-05T08:38:36Z"},{"alias_kind":"pith_short_8","alias_value":"FXSWNDEH","created_at":"2026-07-05T08:38:36Z"}],"graph_snapshots":[{"event_id":"sha256:dbf5ec4cd57fa15ca495a21e78cd712a4472294ae95d37f42d83f94864b74281","target":"graph","created_at":"2026-07-05T08:38:36Z","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/2401.17780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only provides sublinear regret guarantees and fails to ensure convergence to optimal policies. In this paper, we introduce a novel policy gradient PD algorithm with uniform probably approximate correctness (Uniform-PAC) guarantees, simultaneously ensuring convergence to optimal policies, sublinear regret, and polynomial sample complexity for any target accuracy. ","authors_text":"Akiyoshi Sannai, Masahiro Kato, Sho Sonoda, Soichiro Nishimori, Tadashi Kozuno, Toshinori Kitamura, Wataru Kumagai, Yuki Ichihara, Yutaka Matsuo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T12:23:24Z","title":"A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17780","kind":"arxiv","version":3},"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:bcf2ecd71788d6cbf228f19f71e1dd7be52403f32864f78492a4e80805de78b9","target":"record","created_at":"2026-07-05T08:38:36Z","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":"4990f7d94aae90a767e6c57cb74935c0bbf99934dd9184471d7ca1b3e2a7d0f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T12:23:24Z","title_canon_sha256":"5f668df3418e6c36abfd1909ef7949baab9f3d5ed242ebbda248cfd396c7fb3c"},"schema_version":"1.0","source":{"id":"2401.17780","kind":"arxiv","version":3}},"canonical_sha256":"2de5668c8771f5ba10d2c2cb645ce16d7e59438f0831b97828f5b632e7d5b2e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2de5668c8771f5ba10d2c2cb645ce16d7e59438f0831b97828f5b632e7d5b2e6","first_computed_at":"2026-07-05T08:38:36.108787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:36.108787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xpmW4xJIDya59BdM6rVSzcwNVJyolqCOyltg8hcyLNtUsk/acOCF8QXd4/2u0Vyi/3CxavBA7RjbnaN7+8LABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:36.109375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17780","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcf2ecd71788d6cbf228f19f71e1dd7be52403f32864f78492a4e80805de78b9","sha256:dbf5ec4cd57fa15ca495a21e78cd712a4472294ae95d37f42d83f94864b74281"],"state_sha256":"c7f1a394fa63dbda9a6aeb936bf20687b59a33ebabedf5bc0e4069ba66b163cd"}