{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3AC2TDGOEJOJDT2CNBVWQAEQXZ","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":"a458767681732ab11430ccd2c4ef02167f0e87eaf505bd252296104a224840bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-02T09:12:44Z","title_canon_sha256":"451d2538d89ba9d409215acaf1f1c430b24e0c0b955e568c5fdc67dd5d1972c6"},"schema_version":"1.0","source":{"id":"2311.01104","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01104","created_at":"2026-07-05T09:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01104v6","created_at":"2026-07-05T09:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01104","created_at":"2026-07-05T09:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"3AC2TDGOEJOJ","created_at":"2026-07-05T09:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"3AC2TDGOEJOJDT2C","created_at":"2026-07-05T09:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"3AC2TDGO","created_at":"2026-07-05T09:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:5ade78aa94861f4ca4c04c949c3f9c122eac89f3ed14e591c496939b9fc9d237","target":"graph","created_at":"2026-07-05T09:08:21Z","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/2311.01104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sublinear convergence of PPG for sufficiently small step sizes based on the smoothness and the gradient domination properties of the value function. However, as the step size goes to infinity, PPG reduces to the classic policy iteration method, which suggests the convergence of PPG even for large step sizes. In this paper, we fill this gap and show that PPG admits a sublinear convergence for any constant step sizes. Due","authors_text":"Dachao Lin, Jiacai Liu, Ke Wei, Wenye Li, Zhihua Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-02T09:12:44Z","title":"On the Convergence of Projected Policy Gradient for Any Constant Step Sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01104","kind":"arxiv","version":6},"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:fdfa7ed3b7737588c6ef98ac5eecb2a5231cc76869acd62ece4ab1015597abcd","target":"record","created_at":"2026-07-05T09:08:21Z","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":"a458767681732ab11430ccd2c4ef02167f0e87eaf505bd252296104a224840bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-02T09:12:44Z","title_canon_sha256":"451d2538d89ba9d409215acaf1f1c430b24e0c0b955e568c5fdc67dd5d1972c6"},"schema_version":"1.0","source":{"id":"2311.01104","kind":"arxiv","version":6}},"canonical_sha256":"d805a98cce225c91cf42686b680090be7df81ead26215e5d8f456450d0356128","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d805a98cce225c91cf42686b680090be7df81ead26215e5d8f456450d0356128","first_computed_at":"2026-07-05T09:08:21.583544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:21.583544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AUK4b/npKaXUPn2Ym54qJuFa/nYZlaKgjDSNnBUbdBTakl5fqHS45/aGS09G8F7tzLd2IlrIauImcihSO4nRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:21.584101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01104","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdfa7ed3b7737588c6ef98ac5eecb2a5231cc76869acd62ece4ab1015597abcd","sha256:5ade78aa94861f4ca4c04c949c3f9c122eac89f3ed14e591c496939b9fc9d237"],"state_sha256":"06905e21ece4d7c1c5b78053085d01bd39fd92f0b03360da135292015e2d440f"}