{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7SD7GX6HC3VOV7EVECFJF643YG","short_pith_number":"pith:7SD7GX6H","schema_version":"1.0","canonical_sha256":"fc87f35fc716eaeafc95208a92fb9bc1bb85b4dc8658b567efc51a5c1f4ee74e","source":{"kind":"arxiv","id":"2407.16602","version":2},"attestation_state":"computed","paper":{"title":"Functional Acceleration for Policy Mirror Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Veronica Chelu","submitted_at":"2024-07-23T16:04:55Z","abstract_excerpt":"We apply functional acceleration to the Policy Mirror Descent (PMD) general family of algorithms, which cover a wide range of novel and fundamental methods in Reinforcement Learning (RL). Leveraging duality, we propose a momentum-based PMD update. By taking the functional route, our approach is independent of the policy parametrization and applicable to large-scale optimization, covering previous applications of momentum at the level of policy parameters as a special case. We theoretically analyze several properties of this approach and complement with a numerical ablation study, which serves "},"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":"2407.16602","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T16:04:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6fd4be3b746bb8b623452ecd16231e2e4cd61b8b519d4960ef8a75aa50b78f57","abstract_canon_sha256":"ad57e79ed393723fe86d6284d2e20074d5efb1c8860baa460f5cd73875ebecee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:34.933387Z","signature_b64":"K7eglEJpDuu8rZhXfJPbr71C8Cge02H+FmnRGqgTwmiNhYeLgp95b8gmKiL50LCElXFClASEbRLnavcn0x6uBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc87f35fc716eaeafc95208a92fb9bc1bb85b4dc8658b567efc51a5c1f4ee74e","last_reissued_at":"2026-07-05T10:38:34.932915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:34.932915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Functional Acceleration for Policy Mirror Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Veronica Chelu","submitted_at":"2024-07-23T16:04:55Z","abstract_excerpt":"We apply functional acceleration to the Policy Mirror Descent (PMD) general family of algorithms, which cover a wide range of novel and fundamental methods in Reinforcement Learning (RL). Leveraging duality, we propose a momentum-based PMD update. By taking the functional route, our approach is independent of the policy parametrization and applicable to large-scale optimization, covering previous applications of momentum at the level of policy parameters as a special case. We theoretically analyze several properties of this approach and complement with a numerical ablation study, which serves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16602","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/2407.16602/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":"2407.16602","created_at":"2026-07-05T10:38:34.932966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16602v2","created_at":"2026-07-05T10:38:34.932966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16602","created_at":"2026-07-05T10:38:34.932966+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SD7GX6HC3VO","created_at":"2026-07-05T10:38:34.932966+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SD7GX6HC3VOV7EV","created_at":"2026-07-05T10:38:34.932966+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SD7GX6H","created_at":"2026-07-05T10:38:34.932966+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/7SD7GX6HC3VOV7EVECFJF643YG","json":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG.json","graph_json":"https://pith.science/api/pith-number/7SD7GX6HC3VOV7EVECFJF643YG/graph.json","events_json":"https://pith.science/api/pith-number/7SD7GX6HC3VOV7EVECFJF643YG/events.json","paper":"https://pith.science/paper/7SD7GX6H"},"agent_actions":{"view_html":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG","download_json":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG.json","view_paper":"https://pith.science/paper/7SD7GX6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16602&json=true","fetch_graph":"https://pith.science/api/pith-number/7SD7GX6HC3VOV7EVECFJF643YG/graph.json","fetch_events":"https://pith.science/api/pith-number/7SD7GX6HC3VOV7EVECFJF643YG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG/action/storage_attestation","attest_author":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG/action/author_attestation","sign_citation":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG/action/citation_signature","submit_replication":"https://pith.science/pith/7SD7GX6HC3VOV7EVECFJF643YG/action/replication_record"}},"created_at":"2026-07-05T10:38:34.932966+00:00","updated_at":"2026-07-05T10:38:34.932966+00:00"}