{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XYDGOYHYDGSTONO5MOID5RCRPQ","short_pith_number":"pith:XYDGOYHY","schema_version":"1.0","canonical_sha256":"be066760f819a53735dd63903ec4517c15f37c0abb0dd3d0ed1637161b997d80","source":{"kind":"arxiv","id":"2605.14982","version":1},"attestation_state":"computed","paper":{"title":"Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sanjeev Manivannan, Shuban V","submitted_at":"2026-05-14T15:46:27Z","abstract_excerpt":"We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points under suitable assumptions. However, these methods rely on first-order updates. In contrast, second-order optimization provides principled curvature-aware updates that are proven to accelerate convergence, but its application in RL is limited by the computational complexity of Hessian estimation. In this work, we analyze second-order approximations for the ac"},"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":"2605.14982","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T15:46:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a61aa3fb6328845f77aa519d0b7f33294e498d066059ddbd328e0bc5450d4e0e","abstract_canon_sha256":"5906d02392c7c54537a091eaee7f64a57bc6477e63d29899720b271b3bb95f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.101995Z","signature_b64":"74pNmLFna4g/ILZNCBPtNm7Ivj+xxqLNsGTqA07+7qzWpR5OAp0faDaZub4ciYfhpUBji+A6IJ1OVHyIR+AiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be066760f819a53735dd63903ec4517c15f37c0abb0dd3d0ed1637161b997d80","last_reissued_at":"2026-05-17T23:38:55.101395Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.101395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sanjeev Manivannan, Shuban V","submitted_at":"2026-05-14T15:46:27Z","abstract_excerpt":"We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points under suitable assumptions. However, these methods rely on first-order updates. In contrast, second-order optimization provides principled curvature-aware updates that are proven to accelerate convergence, but its application in RL is limited by the computational complexity of Hessian estimation. In this work, we analyze second-order approximations for the ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14982","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":""},"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":"2605.14982","created_at":"2026-05-17T23:38:55.101485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14982v1","created_at":"2026-05-17T23:38:55.101485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14982","created_at":"2026-05-17T23:38:55.101485+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYDGOYHYDGST","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYDGOYHYDGSTONO5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYDGOYHY","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ","json":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ.json","graph_json":"https://pith.science/api/pith-number/XYDGOYHYDGSTONO5MOID5RCRPQ/graph.json","events_json":"https://pith.science/api/pith-number/XYDGOYHYDGSTONO5MOID5RCRPQ/events.json","paper":"https://pith.science/paper/XYDGOYHY"},"agent_actions":{"view_html":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ","download_json":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ.json","view_paper":"https://pith.science/paper/XYDGOYHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14982&json=true","fetch_graph":"https://pith.science/api/pith-number/XYDGOYHYDGSTONO5MOID5RCRPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XYDGOYHYDGSTONO5MOID5RCRPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ/action/storage_attestation","attest_author":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ/action/author_attestation","sign_citation":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ/action/citation_signature","submit_replication":"https://pith.science/pith/XYDGOYHYDGSTONO5MOID5RCRPQ/action/replication_record"}},"created_at":"2026-05-17T23:38:55.101485+00:00","updated_at":"2026-05-17T23:38:55.101485+00:00"}