{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BQTBLZU4PHLDUZ2HEESTZ5HM34","short_pith_number":"pith:BQTBLZU4","canonical_record":{"source":{"id":"2404.03372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T11:16:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"346e18a9279ca85bffe276daf2117706bdd0660303491c24ac3bdf0ed2992fd0","abstract_canon_sha256":"f9ac2d8c5ee824c8897da7e55ac44f523a2ce4c48464fe4911b04204cdb59e34"},"schema_version":"1.0"},"canonical_sha256":"0c2615e69c79d63a674721253cf4ecdf2b263470f4b0c5eb70a3c689482b1928","source":{"kind":"arxiv","id":"2404.03372","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03372","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03372v2","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03372","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"BQTBLZU4PHLD","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"BQTBLZU4PHLDUZ2H","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"BQTBLZU4","created_at":"2026-07-05T08:06:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BQTBLZU4PHLDUZ2HEESTZ5HM34","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T11:16:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"346e18a9279ca85bffe276daf2117706bdd0660303491c24ac3bdf0ed2992fd0","abstract_canon_sha256":"f9ac2d8c5ee824c8897da7e55ac44f523a2ce4c48464fe4911b04204cdb59e34"},"schema_version":"1.0"},"canonical_sha256":"0c2615e69c79d63a674721253cf4ecdf2b263470f4b0c5eb70a3c689482b1928","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:48.271340Z","signature_b64":"vXhiA5oqhAdkr1BvXcv7kiRb1rIS7yQDMQLBi50KQlsxxJKIwLE/En1WssoSmeeCPf86TRCxPxazYUw2M3KeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c2615e69c79d63a674721253cf4ecdf2b263470f4b0c5eb70a3c689482b1928","last_reissued_at":"2026-07-05T08:06:48.270904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:48.270904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03372","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":"2026-07-05T08:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"883XlcKWbINqiYetckY0IPSOVILIiMypbhumh1GMzeiiN2u0fZMIcYngHL4uFgsdi0D3xqCt/vCcZkNWagBzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:25:15.760359Z"},"content_sha256":"09a46b8d287a255c16c7f204d19c4b2cddd0bb43eb5c7c8a357628d3327627f3","schema_version":"1.0","event_id":"sha256:09a46b8d287a255c16c7f204d19c4b2cddd0bb43eb5c7c8a357628d3327627f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BQTBLZU4PHLDUZ2HEESTZ5HM34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Elementary Analysis of Policy Gradient Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jiacai Liu, Ke Wei, Wenye Li","submitted_at":"2024-04-04T11:16:16Z","abstract_excerpt":"Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent activities in studying these algorithms from the theoretical aspect. Despite this, their convergence behavior is still not fully understood, even given the access to exact policy evaluations. In this paper, we focus on the discounted MDP setting and conduct a systematic study of the aforementioned policy optimization methods. Several novel results are presented, incl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03372","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/2404.03372/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":"2026-07-05T08:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OopbeZfE3IeDKktSIKGEId8GaEiAFdWCGLL93RPdJp0wf/WwuVunQE9GwVfoZ9PKdoDV0EvE7ANxEo+9sjhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:25:15.761789Z"},"content_sha256":"27ecaec79c1393d26ed69aaccdd25fcc837808ef29994587ada8ea5ee5670060","schema_version":"1.0","event_id":"sha256:27ecaec79c1393d26ed69aaccdd25fcc837808ef29994587ada8ea5ee5670060"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34/bundle.json","state_url":"https://pith.science/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34/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":"2026-08-05T14:25:15Z","links":{"resolver":"https://pith.science/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34","bundle":"https://pith.science/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34/bundle.json","state":"https://pith.science/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQTBLZU4PHLDUZ2HEESTZ5HM34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQTBLZU4PHLDUZ2HEESTZ5HM34","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":"f9ac2d8c5ee824c8897da7e55ac44f523a2ce4c48464fe4911b04204cdb59e34","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T11:16:16Z","title_canon_sha256":"346e18a9279ca85bffe276daf2117706bdd0660303491c24ac3bdf0ed2992fd0"},"schema_version":"1.0","source":{"id":"2404.03372","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03372","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03372v2","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03372","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"BQTBLZU4PHLD","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"BQTBLZU4PHLDUZ2H","created_at":"2026-07-05T08:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"BQTBLZU4","created_at":"2026-07-05T08:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:27ecaec79c1393d26ed69aaccdd25fcc837808ef29994587ada8ea5ee5670060","target":"graph","created_at":"2026-07-05T08:06:48Z","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/2404.03372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent activities in studying these algorithms from the theoretical aspect. Despite this, their convergence behavior is still not fully understood, even given the access to exact policy evaluations. In this paper, we focus on the discounted MDP setting and conduct a systematic study of the aforementioned policy optimization methods. Several novel results are presented, incl","authors_text":"Jiacai Liu, Ke Wei, Wenye Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T11:16:16Z","title":"Elementary Analysis of Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03372","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":"sha256:09a46b8d287a255c16c7f204d19c4b2cddd0bb43eb5c7c8a357628d3327627f3","target":"record","created_at":"2026-07-05T08:06:48Z","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":"f9ac2d8c5ee824c8897da7e55ac44f523a2ce4c48464fe4911b04204cdb59e34","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-04-04T11:16:16Z","title_canon_sha256":"346e18a9279ca85bffe276daf2117706bdd0660303491c24ac3bdf0ed2992fd0"},"schema_version":"1.0","source":{"id":"2404.03372","kind":"arxiv","version":2}},"canonical_sha256":"0c2615e69c79d63a674721253cf4ecdf2b263470f4b0c5eb70a3c689482b1928","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c2615e69c79d63a674721253cf4ecdf2b263470f4b0c5eb70a3c689482b1928","first_computed_at":"2026-07-05T08:06:48.270904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:48.270904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vXhiA5oqhAdkr1BvXcv7kiRb1rIS7yQDMQLBi50KQlsxxJKIwLE/En1WssoSmeeCPf86TRCxPxazYUw2M3KeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:48.271340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03372","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a46b8d287a255c16c7f204d19c4b2cddd0bb43eb5c7c8a357628d3327627f3","sha256:27ecaec79c1393d26ed69aaccdd25fcc837808ef29994587ada8ea5ee5670060"],"state_sha256":"e6d88a624a73d2e5806a6d374a8fb4128ed7319ec99b3fae8e80c28fa4d69257"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9W1p4bavVbdZGR53Et1H9lKrfybN7x0GqMKp1v65yjvpUkuSNDeXJ8f58GpaovYHoXee+sDLdir8SdrRVv+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:25:15.770328Z","bundle_sha256":"57cbd98ca36f2d45d14bb4d0d5d65b1e56800244d8f11e9ccf2c024664ef4453"}}