{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LJDVAS7X7KTREGZM76ION7DXY6","short_pith_number":"pith:LJDVAS7X","schema_version":"1.0","canonical_sha256":"5a47504bf7faa7121b2cff90e6fc77c7bedf8d81c3d17208507408695bec0279","source":{"kind":"arxiv","id":"2306.10486","version":1},"attestation_state":"computed","paper":{"title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amrit Singh Bedi, Di Wang, Mudit Gaur, Vaneet Aggarwal","submitted_at":"2023-06-18T06:22:04Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.10486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T06:22:04Z","cross_cats_sorted":[],"title_canon_sha256":"409532d6962adcb018aa3881b3bc78db534ee58f5f74f41ec86df1f01b4775a0","abstract_canon_sha256":"e66a68aaeb7689250bb63c92b89785ca9aef816392e9da59e3fd5e7f3dd70c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:38.435568Z","signature_b64":"+7cMdAVM4e1/rLP/LSvdXuBlax48CJVL9L6+3a2nqo3cAQ0qmBrOJPerlJvET0a9bN0FYrl09cED0v9QxQKbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a47504bf7faa7121b2cff90e6fc77c7bedf8d81c3d17208507408695bec0279","last_reissued_at":"2026-07-05T06:21:38.435185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:38.435185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amrit Singh Bedi, Di Wang, Mudit Gaur, Vaneet Aggarwal","submitted_at":"2023-06-18T06:22:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10486","kind":"arxiv","version":1},"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/2306.10486/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.10486","created_at":"2026-07-05T06:21:38.435239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10486v1","created_at":"2026-07-05T06:21:38.435239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10486","created_at":"2026-07-05T06:21:38.435239+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJDVAS7X7KTR","created_at":"2026-07-05T06:21:38.435239+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJDVAS7X7KTREGZM","created_at":"2026-07-05T06:21:38.435239+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJDVAS7X","created_at":"2026-07-05T06:21:38.435239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18433","citing_title":"Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6","json":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6.json","graph_json":"https://pith.science/api/pith-number/LJDVAS7X7KTREGZM76ION7DXY6/graph.json","events_json":"https://pith.science/api/pith-number/LJDVAS7X7KTREGZM76ION7DXY6/events.json","paper":"https://pith.science/paper/LJDVAS7X"},"agent_actions":{"view_html":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6","download_json":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6.json","view_paper":"https://pith.science/paper/LJDVAS7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10486&json=true","fetch_graph":"https://pith.science/api/pith-number/LJDVAS7X7KTREGZM76ION7DXY6/graph.json","fetch_events":"https://pith.science/api/pith-number/LJDVAS7X7KTREGZM76ION7DXY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6/action/storage_attestation","attest_author":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6/action/author_attestation","sign_citation":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6/action/citation_signature","submit_replication":"https://pith.science/pith/LJDVAS7X7KTREGZM76ION7DXY6/action/replication_record"}},"created_at":"2026-07-05T06:21:38.435239+00:00","updated_at":"2026-07-05T06:21:38.435239+00:00"}