{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QXJCMMPVEUMVKDMCRSHERIMEEG","short_pith_number":"pith:QXJCMMPV","canonical_record":{"source":{"id":"1909.01150","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T15:38:19Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5a0393eaade6b21a7e94afea85d59993ddff479dd0b5e85dcd3f5bdaaa9f567a","abstract_canon_sha256":"493f4bbb9783eeca1e26fd4df96313f3bcf079d16f2be62f1f74e638cf2a4050"},"schema_version":"1.0"},"canonical_sha256":"85d22631f52519550d828c8e48a18421b5c530b64968d345d0e842ce662cfd5b","source":{"kind":"arxiv","id":"1909.01150","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01150","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01150v3","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01150","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"QXJCMMPVEUMV","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"QXJCMMPVEUMVKDMC","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"QXJCMMPV","created_at":"2026-07-05T01:11:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QXJCMMPVEUMVKDMCRSHERIMEEG","target":"record","payload":{"canonical_record":{"source":{"id":"1909.01150","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T15:38:19Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5a0393eaade6b21a7e94afea85d59993ddff479dd0b5e85dcd3f5bdaaa9f567a","abstract_canon_sha256":"493f4bbb9783eeca1e26fd4df96313f3bcf079d16f2be62f1f74e638cf2a4050"},"schema_version":"1.0"},"canonical_sha256":"85d22631f52519550d828c8e48a18421b5c530b64968d345d0e842ce662cfd5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:41.465514Z","signature_b64":"xzbfrvRASVdsSpKk71donbi9h3vEQkoSlpii+JQH5cL1DHvgOkXaJ+r5G+8UUeKIywksgW7v2KQqXnisbAAsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d22631f52519550d828c8e48a18421b5c530b64968d345d0e842ce662cfd5b","last_reissued_at":"2026-07-05T01:11:41.464946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:41.464946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.01150","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wE97Qn3aFc+VhrbVABN0Vuw9ShymVqttUNPg63woaHIk/0ZX+I/82FZlikMEWbM8+cg26wjjiRHkv6R3+O2MBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T04:19:30.157070Z"},"content_sha256":"784da1b875dc6fd921c3ce99e7372934c7767826b05515e7bcff306f1e13333b","schema_version":"1.0","event_id":"sha256:784da1b875dc6fd921c3ce99e7372934c7767826b05515e7bcff306f1e13333b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QXJCMMPVEUMVKDMCRSHERIMEEG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lingxiao Wang, Qi Cai, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-08-29T15:38:19Z","abstract_excerpt":"Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such \"neural\" policy gradient methods converge to globally optimal policies and whether they even converge at all. We answer both the questions affirmatively in the overparameterized regime. In detail, we prove that neural natural policy gradient converges to a globally optimal policy at a sublinear rate. Also, we show that neural vanilla policy gradient converges sublinearly to a statio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01150","kind":"arxiv","version":3},"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/1909.01150/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":"2026-07-05T01:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+euTRTKfesnERRvIvO6OoMdPiRmcmcVrjVc/b8701/wpDRm+id5WX2kC23Q5FGf4wD8EUKB00xJurdj79m6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T04:19:30.157471Z"},"content_sha256":"a337d169af0d7555e0fbb527a15283e9081bd311448bb7ce4530a9aeb18f779b","schema_version":"1.0","event_id":"sha256:a337d169af0d7555e0fbb527a15283e9081bd311448bb7ce4530a9aeb18f779b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXJCMMPVEUMVKDMCRSHERIMEEG/bundle.json","state_url":"https://pith.science/pith/QXJCMMPVEUMVKDMCRSHERIMEEG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXJCMMPVEUMVKDMCRSHERIMEEG/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":"2026-07-24T04:19:30Z","links":{"resolver":"https://pith.science/pith/QXJCMMPVEUMVKDMCRSHERIMEEG","bundle":"https://pith.science/pith/QXJCMMPVEUMVKDMCRSHERIMEEG/bundle.json","state":"https://pith.science/pith/QXJCMMPVEUMVKDMCRSHERIMEEG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXJCMMPVEUMVKDMCRSHERIMEEG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QXJCMMPVEUMVKDMCRSHERIMEEG","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":"493f4bbb9783eeca1e26fd4df96313f3bcf079d16f2be62f1f74e638cf2a4050","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T15:38:19Z","title_canon_sha256":"5a0393eaade6b21a7e94afea85d59993ddff479dd0b5e85dcd3f5bdaaa9f567a"},"schema_version":"1.0","source":{"id":"1909.01150","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01150","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01150v3","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01150","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"QXJCMMPVEUMV","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"QXJCMMPVEUMVKDMC","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"QXJCMMPV","created_at":"2026-07-05T01:11:41Z"}],"graph_snapshots":[{"event_id":"sha256:a337d169af0d7555e0fbb527a15283e9081bd311448bb7ce4530a9aeb18f779b","target":"graph","created_at":"2026-07-05T01:11:41Z","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/1909.01150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such \"neural\" policy gradient methods converge to globally optimal policies and whether they even converge at all. We answer both the questions affirmatively in the overparameterized regime. In detail, we prove that neural natural policy gradient converges to a globally optimal policy at a sublinear rate. Also, we show that neural vanilla policy gradient converges sublinearly to a statio","authors_text":"Lingxiao Wang, Qi Cai, Zhaoran Wang, Zhuoran Yang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T15:38:19Z","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01150","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":"sha256:784da1b875dc6fd921c3ce99e7372934c7767826b05515e7bcff306f1e13333b","target":"record","created_at":"2026-07-05T01:11:41Z","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":"493f4bbb9783eeca1e26fd4df96313f3bcf079d16f2be62f1f74e638cf2a4050","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T15:38:19Z","title_canon_sha256":"5a0393eaade6b21a7e94afea85d59993ddff479dd0b5e85dcd3f5bdaaa9f567a"},"schema_version":"1.0","source":{"id":"1909.01150","kind":"arxiv","version":3}},"canonical_sha256":"85d22631f52519550d828c8e48a18421b5c530b64968d345d0e842ce662cfd5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85d22631f52519550d828c8e48a18421b5c530b64968d345d0e842ce662cfd5b","first_computed_at":"2026-07-05T01:11:41.464946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:41.464946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xzbfrvRASVdsSpKk71donbi9h3vEQkoSlpii+JQH5cL1DHvgOkXaJ+r5G+8UUeKIywksgW7v2KQqXnisbAAsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:41.465514Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01150","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:784da1b875dc6fd921c3ce99e7372934c7767826b05515e7bcff306f1e13333b","sha256:a337d169af0d7555e0fbb527a15283e9081bd311448bb7ce4530a9aeb18f779b"],"state_sha256":"6df4bfd94c74d1aa1a60c8ac138567380cd47966f313c786cd55a78fcfb2650f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DcKOvJYAxYoKqK4uGBugDXCHwY8AVAIf7XS7y2QBrAs5OQRuxJ2CCq5MV3bGsHZ1S+AxOE8Wv8fF9DXQ1Gf0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T04:19:30.159694Z","bundle_sha256":"11287c91b01cdc2b0a9a3173d43a2cf56554306320a503f727e7b3dfd9151dd0"}}