{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IQXURC25FVTJVWJU3UDCKE7Q7F","short_pith_number":"pith:IQXURC25","schema_version":"1.0","canonical_sha256":"442f488b5d2d669ad934dd062513f0f972bced2ce7f759b175455f4343ca8f01","source":{"kind":"arxiv","id":"2007.06680","version":2},"attestation_state":"computed","paper":{"title":"Momentum-Based Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feihu Huang, Heng Huang, Jian Pei, Shangqian Gao","submitted_at":"2020-07-13T20:44:15Z","abstract_excerpt":"In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require any large batches. Specifically, we propose a fast important-sampling momentum-based policy gradient (IS-MBPG) method based on a new momentum-based variance reduced technique and the importance sampling technique. We also propose a fast Hessian-aided momentum-based policy gradient (HA-MBPG) method based on the momentum-based variance reduced technique and the Hessian-aided technique. Moreover, we prove that both the"},"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":"2007.06680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T20:44:15Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"116807519ae2462bac3fb93a893cdd2621d801757865201a8889e1f20f973659","abstract_canon_sha256":"88603dd53f63655ebbac71ea8f56e3d17a0ce2196bc4def7ff7a1fbef0a5890a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:13.512533Z","signature_b64":"CEuYd5Ua2Z1LwDEU+jT0bwtWQM8vJA4Sex2Ea3aMyZQbCAOR0+zBfOTcd9XhrhS3lTHAw74RjqDZ8LJLSHcEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"442f488b5d2d669ad934dd062513f0f972bced2ce7f759b175455f4343ca8f01","last_reissued_at":"2026-07-05T01:25:13.512076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:13.512076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Momentum-Based Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feihu Huang, Heng Huang, Jian Pei, Shangqian Gao","submitted_at":"2020-07-13T20:44:15Z","abstract_excerpt":"In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require any large batches. Specifically, we propose a fast important-sampling momentum-based policy gradient (IS-MBPG) method based on a new momentum-based variance reduced technique and the importance sampling technique. We also propose a fast Hessian-aided momentum-based policy gradient (HA-MBPG) method based on the momentum-based variance reduced technique and the Hessian-aided technique. Moreover, we prove that both the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06680","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/2007.06680/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":"2007.06680","created_at":"2026-07-05T01:25:13.512137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06680v2","created_at":"2026-07-05T01:25:13.512137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06680","created_at":"2026-07-05T01:25:13.512137+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQXURC25FVTJ","created_at":"2026-07-05T01:25:13.512137+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQXURC25FVTJVWJU","created_at":"2026-07-05T01:25:13.512137+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQXURC25","created_at":"2026-07-05T01:25:13.512137+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/IQXURC25FVTJVWJU3UDCKE7Q7F","json":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F.json","graph_json":"https://pith.science/api/pith-number/IQXURC25FVTJVWJU3UDCKE7Q7F/graph.json","events_json":"https://pith.science/api/pith-number/IQXURC25FVTJVWJU3UDCKE7Q7F/events.json","paper":"https://pith.science/paper/IQXURC25"},"agent_actions":{"view_html":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F","download_json":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F.json","view_paper":"https://pith.science/paper/IQXURC25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06680&json=true","fetch_graph":"https://pith.science/api/pith-number/IQXURC25FVTJVWJU3UDCKE7Q7F/graph.json","fetch_events":"https://pith.science/api/pith-number/IQXURC25FVTJVWJU3UDCKE7Q7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F/action/storage_attestation","attest_author":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F/action/author_attestation","sign_citation":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F/action/citation_signature","submit_replication":"https://pith.science/pith/IQXURC25FVTJVWJU3UDCKE7Q7F/action/replication_record"}},"created_at":"2026-07-05T01:25:13.512137+00:00","updated_at":"2026-07-05T01:25:13.512137+00:00"}