{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7SD7GX6HC3VOV7EVECFJF643YG","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":"ad57e79ed393723fe86d6284d2e20074d5efb1c8860baa460f5cd73875ebecee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T16:04:55Z","title_canon_sha256":"6fd4be3b746bb8b623452ecd16231e2e4cd61b8b519d4960ef8a75aa50b78f57"},"schema_version":"1.0","source":{"id":"2407.16602","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16602","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16602v2","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16602","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"7SD7GX6HC3VO","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"7SD7GX6HC3VOV7EV","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"7SD7GX6H","created_at":"2026-07-05T10:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:f99df245c22621d7a06f10a39744d5dfd536d40942dd269c68ac99a6154024cb","target":"graph","created_at":"2026-07-05T10:38:34Z","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/2407.16602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Doina Precup, Veronica Chelu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T16:04:55Z","title":"Functional Acceleration for Policy Mirror Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16602","kind":"arxiv","version":2},"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":"sha256:8d43f3973b4e4cbae0c3319a40795a9f99f542008e604774537b97b5bd8b1df7","target":"record","created_at":"2026-07-05T10:38:34Z","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":"ad57e79ed393723fe86d6284d2e20074d5efb1c8860baa460f5cd73875ebecee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T16:04:55Z","title_canon_sha256":"6fd4be3b746bb8b623452ecd16231e2e4cd61b8b519d4960ef8a75aa50b78f57"},"schema_version":"1.0","source":{"id":"2407.16602","kind":"arxiv","version":2}},"canonical_sha256":"fc87f35fc716eaeafc95208a92fb9bc1bb85b4dc8658b567efc51a5c1f4ee74e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc87f35fc716eaeafc95208a92fb9bc1bb85b4dc8658b567efc51a5c1f4ee74e","first_computed_at":"2026-07-05T10:38:34.932915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:34.932915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K7eglEJpDuu8rZhXfJPbr71C8Cge02H+FmnRGqgTwmiNhYeLgp95b8gmKiL50LCElXFClASEbRLnavcn0x6uBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:34.933387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16602","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d43f3973b4e4cbae0c3319a40795a9f99f542008e604774537b97b5bd8b1df7","sha256:f99df245c22621d7a06f10a39744d5dfd536d40942dd269c68ac99a6154024cb"],"state_sha256":"af4d2b10a6e35ac4f0c6fd320f2c1cf3180809702e0c360efb4642faf61aa379"}