{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IPWRSR7LOYT5K7Y22YWGKDVABN","short_pith_number":"pith:IPWRSR7L","schema_version":"1.0","canonical_sha256":"43ed1947eb7627d57f1ad62c650ea00b790ccae6f647febfe16ffb533eff23f1","source":{"kind":"arxiv","id":"2506.01597","version":1},"attestation_state":"computed","paper":{"title":"Policy Newton Algorithm in Reproducing Kernel Hilbert Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Huaze Tang, Wenbo Ding, Yixian Zhang","submitted_at":"2025-06-02T12:32:52Z","abstract_excerpt":"Reinforcement learning (RL) policies represented in Reproducing Kernel Hilbert Spaces (RKHS) offer powerful representational capabilities. While second-order optimization methods like Newton's method demonstrate faster convergence than first-order approaches, current RKHS-based policy optimization remains constrained to first-order techniques. This limitation stems primarily from the intractability of explicitly computing and inverting the infinite-dimensional Hessian operator in RKHS. We introduce Policy Newton in RKHS, the first second-order optimization framework specifically designed for R"},"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":"2506.01597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T12:32:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bd60d7c9ac6a87f7aa6ff7ba28e7167b0c97ad6914f36d49695970356d65313","abstract_canon_sha256":"b09850ecdc370cd82c1d358d6bfdbe37d1a984f3753236e8bbf2457d4be4856d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:16.459586Z","signature_b64":"ZRjBhKRA1nJDFX0ka2wUj7TkOH5xEGGKlp346+R22ZicPMMxtWtZ+SY6QYwbzA7EdV55Gs68hlPoEGD5XKdeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43ed1947eb7627d57f1ad62c650ea00b790ccae6f647febfe16ffb533eff23f1","last_reissued_at":"2026-07-05T11:14:16.459031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:16.459031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Newton Algorithm in Reproducing Kernel Hilbert Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Huaze Tang, Wenbo Ding, Yixian Zhang","submitted_at":"2025-06-02T12:32:52Z","abstract_excerpt":"Reinforcement learning (RL) policies represented in Reproducing Kernel Hilbert Spaces (RKHS) offer powerful representational capabilities. While second-order optimization methods like Newton's method demonstrate faster convergence than first-order approaches, current RKHS-based policy optimization remains constrained to first-order techniques. This limitation stems primarily from the intractability of explicitly computing and inverting the infinite-dimensional Hessian operator in RKHS. We introduce Policy Newton in RKHS, the first second-order optimization framework specifically designed for R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01597","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/2506.01597/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":"2506.01597","created_at":"2026-07-05T11:14:16.459090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01597v1","created_at":"2026-07-05T11:14:16.459090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01597","created_at":"2026-07-05T11:14:16.459090+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPWRSR7LOYT5","created_at":"2026-07-05T11:14:16.459090+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPWRSR7LOYT5K7Y2","created_at":"2026-07-05T11:14:16.459090+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPWRSR7L","created_at":"2026-07-05T11:14:16.459090+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/IPWRSR7LOYT5K7Y22YWGKDVABN","json":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN.json","graph_json":"https://pith.science/api/pith-number/IPWRSR7LOYT5K7Y22YWGKDVABN/graph.json","events_json":"https://pith.science/api/pith-number/IPWRSR7LOYT5K7Y22YWGKDVABN/events.json","paper":"https://pith.science/paper/IPWRSR7L"},"agent_actions":{"view_html":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN","download_json":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN.json","view_paper":"https://pith.science/paper/IPWRSR7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01597&json=true","fetch_graph":"https://pith.science/api/pith-number/IPWRSR7LOYT5K7Y22YWGKDVABN/graph.json","fetch_events":"https://pith.science/api/pith-number/IPWRSR7LOYT5K7Y22YWGKDVABN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN/action/storage_attestation","attest_author":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN/action/author_attestation","sign_citation":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN/action/citation_signature","submit_replication":"https://pith.science/pith/IPWRSR7LOYT5K7Y22YWGKDVABN/action/replication_record"}},"created_at":"2026-07-05T11:14:16.459090+00:00","updated_at":"2026-07-05T11:14:16.459090+00:00"}