{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IQXURC25FVTJVWJU3UDCKE7Q7F","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":"88603dd53f63655ebbac71ea8f56e3d17a0ce2196bc4def7ff7a1fbef0a5890a","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T20:44:15Z","title_canon_sha256":"116807519ae2462bac3fb93a893cdd2621d801757865201a8889e1f20f973659"},"schema_version":"1.0","source":{"id":"2007.06680","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06680","created_at":"2026-07-05T01:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06680v2","created_at":"2026-07-05T01:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06680","created_at":"2026-07-05T01:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"IQXURC25FVTJ","created_at":"2026-07-05T01:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"IQXURC25FVTJVWJU","created_at":"2026-07-05T01:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"IQXURC25","created_at":"2026-07-05T01:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:8c25eccc5c37ec89be94d4ddce7cf48ed199fb7440be4021433a8506402746ea","target":"graph","created_at":"2026-07-05T01:25:13Z","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/2007.06680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Feihu Huang, Heng Huang, Jian Pei, Shangqian Gao","cross_cats":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T20:44:15Z","title":"Momentum-Based Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06680","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":"sha256:5294ed9bef26f6349a29755bdecba265d2bf3ac0e5e940ff26aad296c3d2f4cb","target":"record","created_at":"2026-07-05T01:25:13Z","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":"88603dd53f63655ebbac71ea8f56e3d17a0ce2196bc4def7ff7a1fbef0a5890a","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T20:44:15Z","title_canon_sha256":"116807519ae2462bac3fb93a893cdd2621d801757865201a8889e1f20f973659"},"schema_version":"1.0","source":{"id":"2007.06680","kind":"arxiv","version":2}},"canonical_sha256":"442f488b5d2d669ad934dd062513f0f972bced2ce7f759b175455f4343ca8f01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"442f488b5d2d669ad934dd062513f0f972bced2ce7f759b175455f4343ca8f01","first_computed_at":"2026-07-05T01:25:13.512076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:25:13.512076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CEuYd5Ua2Z1LwDEU+jT0bwtWQM8vJA4Sex2Ea3aMyZQbCAOR0+zBfOTcd9XhrhS3lTHAw74RjqDZ8LJLSHcEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:25:13.512533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.06680","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5294ed9bef26f6349a29755bdecba265d2bf3ac0e5e940ff26aad296c3d2f4cb","sha256:8c25eccc5c37ec89be94d4ddce7cf48ed199fb7440be4021433a8506402746ea"],"state_sha256":"11bd6904b52fb3dc4dac5072a5d367c2bd8673183923c7411b1172716705fd09"}