{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GWIO7DMGPIMSGPBCIVTDHSMREX","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":"694aadff59985a93410a11fdc23dc05f84bbe3b128ddf52d4bffd2d102738a73","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T01:33:05Z","title_canon_sha256":"e4f8b3a36d69cd923e4f24e12b374e5af548b14e1c291ff4ba171b0f755102b1"},"schema_version":"1.0","source":{"id":"2010.13272","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13272","created_at":"2026-07-05T06:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13272v4","created_at":"2026-07-05T06:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13272","created_at":"2026-07-05T06:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"GWIO7DMGPIMS","created_at":"2026-07-05T06:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"GWIO7DMGPIMSGPBC","created_at":"2026-07-05T06:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"GWIO7DMG","created_at":"2026-07-05T06:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:40f33ad27a78f9bd98b43c3b825ce910ebc42d66a402879e6a8d0d23e05b7f4e","target":"graph","created_at":"2026-07-05T06:12:21Z","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/2010.13272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variance reduction techniques have been successfully applied to temporal-difference (TD) learning and help to improve the sample complexity in policy evaluation. However, the existing work applied variance reduction to either the less popular one time-scale TD algorithm or the two time-scale GTD algorithm but with a finite number of i.i.d.\\ samples, and both algorithms apply to only the on-policy setting. In this work, we develop a variance reduction scheme for the two time-scale TDC algorithm in the off-policy setting and analyze its non-asymptotic convergence rate over both i.i.d.\\ and Marko","authors_text":"Shaocong Ma, Shaofeng Zou, Yi Zhou","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T01:33:05Z","title":"Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13272","kind":"arxiv","version":4},"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:dafb1257e924ca5fe83f9951055939eb07e334a66398f92ad603beccf70722a6","target":"record","created_at":"2026-07-05T06:12:21Z","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":"694aadff59985a93410a11fdc23dc05f84bbe3b128ddf52d4bffd2d102738a73","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T01:33:05Z","title_canon_sha256":"e4f8b3a36d69cd923e4f24e12b374e5af548b14e1c291ff4ba171b0f755102b1"},"schema_version":"1.0","source":{"id":"2010.13272","kind":"arxiv","version":4}},"canonical_sha256":"3590ef8d867a19233c22456633c99125c7e3e33f649362e982c243efd639a999","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3590ef8d867a19233c22456633c99125c7e3e33f649362e982c243efd639a999","first_computed_at":"2026-07-05T06:12:21.638659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:21.638659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pkfMhgusw763fpFNbqS7VryGXxPZ9I1oZ0MVOvIoqNYcixqCX79kjutAPMn4eMa/7dNWBzdCqjytu6UvS9ikDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:21.639179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.13272","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dafb1257e924ca5fe83f9951055939eb07e334a66398f92ad603beccf70722a6","sha256:40f33ad27a78f9bd98b43c3b825ce910ebc42d66a402879e6a8d0d23e05b7f4e"],"state_sha256":"6bd689be7ea6fec75296bcdd650b1bb84be303791ea8a0722686d5f29b081618"}