{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BGCW7BDB66F4PF3LNPR3RAOZQZ","short_pith_number":"pith:BGCW7BDB","canonical_record":{"source":{"id":"2103.16377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-30T14:17:50Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"74b66ab530d18411b8d4939772ff16de98d71ced183383c647cdd49c9372805a","abstract_canon_sha256":"2fedcab07461294582c952eacb704abf171379e4357bd1b4c4d91d008b346c87"},"schema_version":"1.0"},"canonical_sha256":"09856f8461f78bc7976b6be3b881d9867760c4c69789e3963a84e77705067f1d","source":{"kind":"arxiv","id":"2103.16377","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16377","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16377v1","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16377","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"BGCW7BDB66F4","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"BGCW7BDB66F4PF3L","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"BGCW7BDB","created_at":"2026-07-05T02:27:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BGCW7BDB66F4PF3LNPR3RAOZQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2103.16377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-30T14:17:50Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"74b66ab530d18411b8d4939772ff16de98d71ced183383c647cdd49c9372805a","abstract_canon_sha256":"2fedcab07461294582c952eacb704abf171379e4357bd1b4c4d91d008b346c87"},"schema_version":"1.0"},"canonical_sha256":"09856f8461f78bc7976b6be3b881d9867760c4c69789e3963a84e77705067f1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:51.240121Z","signature_b64":"v9MR1gSdyfK4zOAqCzLj6i+oAvAo5zKyp6oX5wshffRhreaCwL7uf/niw3OF8yIoRmK82Ri2KMXChfUrdJtODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09856f8461f78bc7976b6be3b881d9867760c4c69789e3963a84e77705067f1d","last_reissued_at":"2026-07-05T02:27:51.239742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:51.239742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.16377","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6EK8P/k2hm65GpnWxsjmZIvpiz3ld/om86LOcgGbvbcb2ZzwqxyIjUwgjVNoC75ixPzR9qlo62siSRZmI31CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:28:36.192617Z"},"content_sha256":"9221a447b0ee096227646961dacfb80df0ad8ac07b440ca2c7f900a0e3ad04e0","schema_version":"1.0","event_id":"sha256:9221a447b0ee096227646961dacfb80df0ad8ac07b440ca2c7f900a0e3ad04e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BGCW7BDB66F4PF3LNPR3RAOZQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Shaocong Ma, Shaofeng Zou, Yi Zhou, Ziyi Chen","submitted_at":"2021-03-30T14:17:50Z","abstract_excerpt":"Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under linear function approximation and Markovian sampling, and the algorithm is shown to achieve an $\\epsilon$-stationary point with a sample complexity in the order of $\\mathcal{O}(\\epsilon^{-3})$. Such a high sample complexity is due to the large variance induced by the Markovian samples. In this paper, we propose a variance-reduced Greedy-GQ (VR-Greedy-GQ) algorithm for off-policy optimal control. In particular, the algorithm applies the S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16377","kind":"arxiv","version":1},"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/2103.16377/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ToP56s+7/F4A1K2HCZ0nqhMImOJKC0HA6PYOckTVYmX2njl8gx0HgiGGiCm7VwyamD3OPl+eCPo5AwKmB/XdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:28:36.192997Z"},"content_sha256":"d6d6f17c858a1da4f4bfcd9be1021e045ad2f77e2036851dfdf49ad8c1defbde","schema_version":"1.0","event_id":"sha256:d6d6f17c858a1da4f4bfcd9be1021e045ad2f77e2036851dfdf49ad8c1defbde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ/bundle.json","state_url":"https://pith.science/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-14T12:28:36Z","links":{"resolver":"https://pith.science/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ","bundle":"https://pith.science/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ/bundle.json","state":"https://pith.science/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGCW7BDB66F4PF3LNPR3RAOZQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BGCW7BDB66F4PF3LNPR3RAOZQZ","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":"2fedcab07461294582c952eacb704abf171379e4357bd1b4c4d91d008b346c87","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-30T14:17:50Z","title_canon_sha256":"74b66ab530d18411b8d4939772ff16de98d71ced183383c647cdd49c9372805a"},"schema_version":"1.0","source":{"id":"2103.16377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16377","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16377v1","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16377","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"BGCW7BDB66F4","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"BGCW7BDB66F4PF3L","created_at":"2026-07-05T02:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"BGCW7BDB","created_at":"2026-07-05T02:27:51Z"}],"graph_snapshots":[{"event_id":"sha256:d6d6f17c858a1da4f4bfcd9be1021e045ad2f77e2036851dfdf49ad8c1defbde","target":"graph","created_at":"2026-07-05T02:27:51Z","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/2103.16377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under linear function approximation and Markovian sampling, and the algorithm is shown to achieve an $\\epsilon$-stationary point with a sample complexity in the order of $\\mathcal{O}(\\epsilon^{-3})$. Such a high sample complexity is due to the large variance induced by the Markovian samples. In this paper, we propose a variance-reduced Greedy-GQ (VR-Greedy-GQ) algorithm for off-policy optimal control. In particular, the algorithm applies the S","authors_text":"Shaocong Ma, Shaofeng Zou, Yi Zhou, Ziyi Chen","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-30T14:17:50Z","title":"Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16377","kind":"arxiv","version":1},"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":"sha256:9221a447b0ee096227646961dacfb80df0ad8ac07b440ca2c7f900a0e3ad04e0","target":"record","created_at":"2026-07-05T02:27:51Z","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":"2fedcab07461294582c952eacb704abf171379e4357bd1b4c4d91d008b346c87","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-30T14:17:50Z","title_canon_sha256":"74b66ab530d18411b8d4939772ff16de98d71ced183383c647cdd49c9372805a"},"schema_version":"1.0","source":{"id":"2103.16377","kind":"arxiv","version":1}},"canonical_sha256":"09856f8461f78bc7976b6be3b881d9867760c4c69789e3963a84e77705067f1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09856f8461f78bc7976b6be3b881d9867760c4c69789e3963a84e77705067f1d","first_computed_at":"2026-07-05T02:27:51.239742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:27:51.239742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9MR1gSdyfK4zOAqCzLj6i+oAvAo5zKyp6oX5wshffRhreaCwL7uf/niw3OF8yIoRmK82Ri2KMXChfUrdJtODw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:27:51.240121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.16377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9221a447b0ee096227646961dacfb80df0ad8ac07b440ca2c7f900a0e3ad04e0","sha256:d6d6f17c858a1da4f4bfcd9be1021e045ad2f77e2036851dfdf49ad8c1defbde"],"state_sha256":"03189df02e3c86cb525865b3648cab482d1a2093522d8413ed53f1d3a008fbfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDoQM+aVLzjGBettdI+GEh1pd6/h7lS8QvY/7OoibRpOsC5K+9XJys3ZkKlSj4p1Sq/r/FHt4bkdGOuvlVSvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T12:28:36.195391Z","bundle_sha256":"b6b12300dd6bc49350498eafc081baeca75ac220dc0c34c2c41a2282213d5c5a"}}