{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RMP6D66KEPRXIUPGLVHKN3KWL5","short_pith_number":"pith:RMP6D66K","canonical_record":{"source":{"id":"2107.11433","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-23T19:38:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f3ac2fb68b0e8df7578cb477b3297183a38c38448af917677ceb6dcfc511f617","abstract_canon_sha256":"7fadd3be7b8985ce38c6e5badddd86525597a2c3d3d8123a54015d6a4009fee5"},"schema_version":"1.0"},"canonical_sha256":"8b1fe1fbca23e37451e65d4ea6ed565f42117543f2b1fe174193aae60446a049","source":{"kind":"arxiv","id":"2107.11433","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.11433","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2107.11433v5","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11433","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"RMP6D66KEPRX","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"RMP6D66KEPRXIUPG","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"RMP6D66K","created_at":"2026-07-05T05:17:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RMP6D66KEPRXIUPGLVHKN3KWL5","target":"record","payload":{"canonical_record":{"source":{"id":"2107.11433","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-23T19:38:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f3ac2fb68b0e8df7578cb477b3297183a38c38448af917677ceb6dcfc511f617","abstract_canon_sha256":"7fadd3be7b8985ce38c6e5badddd86525597a2c3d3d8123a54015d6a4009fee5"},"schema_version":"1.0"},"canonical_sha256":"8b1fe1fbca23e37451e65d4ea6ed565f42117543f2b1fe174193aae60446a049","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:08.459101Z","signature_b64":"/E84JUtWXJClnSCruDg3iv28So/4MIwRFMs5rPOPfJF2nK/8wqQ7Vt4vbaZ+lbCrL8t3r5k9+5LHE0kdMqcFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b1fe1fbca23e37451e65d4ea6ed565f42117543f2b1fe174193aae60446a049","last_reissued_at":"2026-07-05T05:17:08.458766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:08.458766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.11433","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SfLEhI3Hv9bd4kQCKrfg7u4ey6yPeT44VCc1anx0ThI74xCRhGQoiwSvkPxJa+yE0DAlVr3gKuW5AOHNSc4MAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:18:07.820829Z"},"content_sha256":"533c007f8478f028d0515ec340ffa9763de0f61e702c8b9f5ddb3150f905a616","schema_version":"1.0","event_id":"sha256:533c007f8478f028d0515ec340ffa9763de0f61e702c8b9f5ddb3150f905a616"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RMP6D66KEPRXIUPGLVHKN3KWL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A general sample complexity analysis of vanilla policy gradient","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Robert M. Gower, Rui Yuan","submitted_at":"2021-07-23T19:38:17Z","abstract_excerpt":"We adapt recent tools developed for the analysis of Stochastic Gradient Descent (SGD) in non-convex optimization to obtain convergence and sample complexity guarantees for the vanilla policy gradient (PG). Our only assumptions are that the expected return is smooth w.r.t. the policy parameters, that its $H$-step truncated gradient is close to the exact gradient, and a certain ABC assumption. This assumption requires the second moment of the estimated gradient to be bounded by $A\\geq 0$ times the suboptimality gap, $B \\geq 0$ times the norm of the full batch gradient and an additive constant $C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11433","kind":"arxiv","version":5},"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/2107.11433/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":"2026-07-05T05:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnC7o1luaHXWHGry6UK74Kl5+A/BCrQseHEJvkNc+sWeHZV05Mc7C116rmwsmGsklciVo8Ie0sx6WrskZCT8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:18:07.821207Z"},"content_sha256":"065b43fff6fddeec8a6c788cfcffadfa44471b0310bec14ee9fd44611ed54f75","schema_version":"1.0","event_id":"sha256:065b43fff6fddeec8a6c788cfcffadfa44471b0310bec14ee9fd44611ed54f75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMP6D66KEPRXIUPGLVHKN3KWL5/bundle.json","state_url":"https://pith.science/pith/RMP6D66KEPRXIUPGLVHKN3KWL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMP6D66KEPRXIUPGLVHKN3KWL5/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":"2026-07-07T11:18:07Z","links":{"resolver":"https://pith.science/pith/RMP6D66KEPRXIUPGLVHKN3KWL5","bundle":"https://pith.science/pith/RMP6D66KEPRXIUPGLVHKN3KWL5/bundle.json","state":"https://pith.science/pith/RMP6D66KEPRXIUPGLVHKN3KWL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMP6D66KEPRXIUPGLVHKN3KWL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RMP6D66KEPRXIUPGLVHKN3KWL5","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":"7fadd3be7b8985ce38c6e5badddd86525597a2c3d3d8123a54015d6a4009fee5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-23T19:38:17Z","title_canon_sha256":"f3ac2fb68b0e8df7578cb477b3297183a38c38448af917677ceb6dcfc511f617"},"schema_version":"1.0","source":{"id":"2107.11433","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.11433","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2107.11433v5","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11433","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"RMP6D66KEPRX","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"RMP6D66KEPRXIUPG","created_at":"2026-07-05T05:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"RMP6D66K","created_at":"2026-07-05T05:17:08Z"}],"graph_snapshots":[{"event_id":"sha256:065b43fff6fddeec8a6c788cfcffadfa44471b0310bec14ee9fd44611ed54f75","target":"graph","created_at":"2026-07-05T05:17:08Z","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/2107.11433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We adapt recent tools developed for the analysis of Stochastic Gradient Descent (SGD) in non-convex optimization to obtain convergence and sample complexity guarantees for the vanilla policy gradient (PG). Our only assumptions are that the expected return is smooth w.r.t. the policy parameters, that its $H$-step truncated gradient is close to the exact gradient, and a certain ABC assumption. This assumption requires the second moment of the estimated gradient to be bounded by $A\\geq 0$ times the suboptimality gap, $B \\geq 0$ times the norm of the full batch gradient and an additive constant $C","authors_text":"Alessandro Lazaric, Robert M. Gower, Rui Yuan","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-23T19:38:17Z","title":"A general sample complexity analysis of vanilla policy gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11433","kind":"arxiv","version":5},"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":"sha256:533c007f8478f028d0515ec340ffa9763de0f61e702c8b9f5ddb3150f905a616","target":"record","created_at":"2026-07-05T05:17:08Z","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":"7fadd3be7b8985ce38c6e5badddd86525597a2c3d3d8123a54015d6a4009fee5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-23T19:38:17Z","title_canon_sha256":"f3ac2fb68b0e8df7578cb477b3297183a38c38448af917677ceb6dcfc511f617"},"schema_version":"1.0","source":{"id":"2107.11433","kind":"arxiv","version":5}},"canonical_sha256":"8b1fe1fbca23e37451e65d4ea6ed565f42117543f2b1fe174193aae60446a049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b1fe1fbca23e37451e65d4ea6ed565f42117543f2b1fe174193aae60446a049","first_computed_at":"2026-07-05T05:17:08.458766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:08.458766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/E84JUtWXJClnSCruDg3iv28So/4MIwRFMs5rPOPfJF2nK/8wqQ7Vt4vbaZ+lbCrL8t3r5k9+5LHE0kdMqcFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:08.459101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.11433","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:533c007f8478f028d0515ec340ffa9763de0f61e702c8b9f5ddb3150f905a616","sha256:065b43fff6fddeec8a6c788cfcffadfa44471b0310bec14ee9fd44611ed54f75"],"state_sha256":"0ba548f66d62a4e1f38157461e06f15515c99dd49a9cf668b04e8cc800fdff7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCgv1WE/J8d7lvWoLe4cwLIA5IsTyFKswIHxlIXo2jwcmn/kKwknudhTWYn6clC5bvuvQqNuI8fjqkKqMuFgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:18:07.823363Z","bundle_sha256":"48eaa369d96e7baf7c5e143736f7f644b6e8b47b04131e0cd8a36e82343a7a2d"}}