{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PSKNJA3ONJ6XCNCLIYIPFBYWTT","short_pith_number":"pith:PSKNJA3O","schema_version":"1.0","canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","source":{"kind":"arxiv","id":"1905.12615","version":1},"attestation_state":"computed","paper":{"title":"An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felicia Gao, Pan Xu, Quanquan Gu","submitted_at":"2019-05-29T17:57:23Z","abstract_excerpt":"We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\\epsilon$-approximate stationary point of the performance function within $O(1/\\epsilon^{5/3})$ trajectories. This sample complexity improves upon the best known result $O(1/\\epsilon^2)$ by a factor of $O(1/\\epsilon^{1/3})$. At the core of our analysis is (i) a tighter upper bound for the variance of importance sampling weights, where we prove that the variance can be controlled "},"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":"1905.12615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T17:57:23Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"8811ec64b1d87946fc3ae8f368eaae526d8974ed295f8580f38543954ec70747","abstract_canon_sha256":"46f1e41bd390d751548d519b78ade71e41c2e60a68a0cc91ab959b0cf1fc58d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:43.814813Z","signature_b64":"EZh+Lw4FTq+KmHJXNZToqZCVl/2Pqkxv+pQ4e/fC4QtZ3QwiimoXAg/E5lGvV85Q4pdEvAX8FD8UU8EnOZaVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","last_reissued_at":"2026-05-17T23:44:43.814211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:43.814211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felicia Gao, Pan Xu, Quanquan Gu","submitted_at":"2019-05-29T17:57:23Z","abstract_excerpt":"We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\\epsilon$-approximate stationary point of the performance function within $O(1/\\epsilon^{5/3})$ trajectories. This sample complexity improves upon the best known result $O(1/\\epsilon^2)$ by a factor of $O(1/\\epsilon^{1/3})$. At the core of our analysis is (i) a tighter upper bound for the variance of importance sampling weights, where we prove that the variance can be controlled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12615","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":""},"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":"1905.12615","created_at":"2026-05-17T23:44:43.814301+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12615v1","created_at":"2026-05-17T23:44:43.814301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12615","created_at":"2026-05-17T23:44:43.814301+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSKNJA3ONJ6X","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSKNJA3ONJ6XCNCL","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSKNJA3O","created_at":"2026-05-18T12:33:24.271573+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/PSKNJA3ONJ6XCNCLIYIPFBYWTT","json":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT.json","graph_json":"https://pith.science/api/pith-number/PSKNJA3ONJ6XCNCLIYIPFBYWTT/graph.json","events_json":"https://pith.science/api/pith-number/PSKNJA3ONJ6XCNCLIYIPFBYWTT/events.json","paper":"https://pith.science/paper/PSKNJA3O"},"agent_actions":{"view_html":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT","download_json":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT.json","view_paper":"https://pith.science/paper/PSKNJA3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12615&json=true","fetch_graph":"https://pith.science/api/pith-number/PSKNJA3ONJ6XCNCLIYIPFBYWTT/graph.json","fetch_events":"https://pith.science/api/pith-number/PSKNJA3ONJ6XCNCLIYIPFBYWTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/action/storage_attestation","attest_author":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/action/author_attestation","sign_citation":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/action/citation_signature","submit_replication":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/action/replication_record"}},"created_at":"2026-05-17T23:44:43.814301+00:00","updated_at":"2026-05-17T23:44:43.814301+00:00"}