{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LJDVAS7X7KTREGZM76ION7DXY6","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":"e66a68aaeb7689250bb63c92b89785ca9aef816392e9da59e3fd5e7f3dd70c45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T06:22:04Z","title_canon_sha256":"409532d6962adcb018aa3881b3bc78db534ee58f5f74f41ec86df1f01b4775a0"},"schema_version":"1.0","source":{"id":"2306.10486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10486","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10486v1","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10486","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"LJDVAS7X7KTR","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"pith_short_16","alias_value":"LJDVAS7X7KTREGZM","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"pith_short_8","alias_value":"LJDVAS7X","created_at":"2026-07-05T06:21:38Z"}],"graph_snapshots":[{"event_id":"sha256:1d95a46628f0bd9600d45a2b8e4d10548b5c0c9dc054ccd516efaf72c778d85a","target":"graph","created_at":"2026-07-05T06:21:38Z","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/2306.10486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic algorithms have shown remarkable success in solving state-of-the-art decision-making problems. However, despite their empirical effectiveness, their theoretical underpinnings remain relatively unexplored, especially with neural network parametrization. In this paper, we delve into the study of a natural actor-critic algorithm that utilizes neural networks to represent the critic. Our aim is to establish sample complexity guarantees for this algorithm, achieving a deeper understanding of its performance characteristics. To achieve that, we propose a Natural Actor-Critic algorithm w","authors_text":"Amrit Singh Bedi, Di Wang, Mudit Gaur, Vaneet Aggarwal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T06:22:04Z","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10486","kind":"arxiv","version":1},"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:c2ed28dc989807bacd012aabd48464ffc5354cc723bfb28e1a7b3c03f1ad2520","target":"record","created_at":"2026-07-05T06:21:38Z","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":"e66a68aaeb7689250bb63c92b89785ca9aef816392e9da59e3fd5e7f3dd70c45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T06:22:04Z","title_canon_sha256":"409532d6962adcb018aa3881b3bc78db534ee58f5f74f41ec86df1f01b4775a0"},"schema_version":"1.0","source":{"id":"2306.10486","kind":"arxiv","version":1}},"canonical_sha256":"5a47504bf7faa7121b2cff90e6fc77c7bedf8d81c3d17208507408695bec0279","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a47504bf7faa7121b2cff90e6fc77c7bedf8d81c3d17208507408695bec0279","first_computed_at":"2026-07-05T06:21:38.435185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:38.435185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7cMdAVM4e1/rLP/LSvdXuBlax48CJVL9L6+3a2nqo3cAQ0qmBrOJPerlJvET0a9bN0FYrl09cED0v9QxQKbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:38.435568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ed28dc989807bacd012aabd48464ffc5354cc723bfb28e1a7b3c03f1ad2520","sha256:1d95a46628f0bd9600d45a2b8e4d10548b5c0c9dc054ccd516efaf72c778d85a"],"state_sha256":"a84c403588b1e16f458bd40565fa7fedb47654a3b3439936e87e8d4c30312a9e"}