{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:C5K4B3XGX56QIFQ3HQJJU77NBB","short_pith_number":"pith:C5K4B3XG","schema_version":"1.0","canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","source":{"kind":"arxiv","id":"1811.06225","version":1},"attestation_state":"computed","paper":{"title":"Reward-estimation variance elimination in sequential decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sergey Pankov","submitted_at":"2018-11-15T08:18:33Z","abstract_excerpt":"Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency. To mitigate this issue, a number of variance-reduction approaches have been proposed. Unfortunately, in the challenging problems with delayed rewards, these approaches either bring a relatively modest improvement or do reduce variance at expense of introducing a bias and undermining convergence. The unbiased methods of gradient estimation, in general, only p"},"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":"1811.06225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8","abstract_canon_sha256":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:38.303345Z","signature_b64":"d4EMc16Q6nkUxSuXoiHqJF/xq5NUaWXoEV78A27OjjJW5jGQVCYqgOcWjRU6QPiptV7Y6Lx2mw96DtrjyjuWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","last_reissued_at":"2026-05-18T00:00:38.302890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:38.302890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-estimation variance elimination in sequential decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sergey Pankov","submitted_at":"2018-11-15T08:18:33Z","abstract_excerpt":"Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency. To mitigate this issue, a number of variance-reduction approaches have been proposed. Unfortunately, in the challenging problems with delayed rewards, these approaches either bring a relatively modest improvement or do reduce variance at expense of introducing a bias and undermining convergence. The unbiased methods of gradient estimation, in general, only p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06225","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":"1811.06225","created_at":"2026-05-18T00:00:38.302959+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.06225v1","created_at":"2026-05-18T00:00:38.302959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06225","created_at":"2026-05-18T00:00:38.302959+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5K4B3XGX56Q","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5K4B3XGX56QIFQ3","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5K4B3XG","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":247,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB","json":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB.json","graph_json":"https://pith.science/api/pith-number/C5K4B3XGX56QIFQ3HQJJU77NBB/graph.json","events_json":"https://pith.science/api/pith-number/C5K4B3XGX56QIFQ3HQJJU77NBB/events.json","paper":"https://pith.science/paper/C5K4B3XG"},"agent_actions":{"view_html":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB","download_json":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB.json","view_paper":"https://pith.science/paper/C5K4B3XG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.06225&json=true","fetch_graph":"https://pith.science/api/pith-number/C5K4B3XGX56QIFQ3HQJJU77NBB/graph.json","fetch_events":"https://pith.science/api/pith-number/C5K4B3XGX56QIFQ3HQJJU77NBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/action/storage_attestation","attest_author":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/action/author_attestation","sign_citation":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/action/citation_signature","submit_replication":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/action/replication_record"}},"created_at":"2026-05-18T00:00:38.302959+00:00","updated_at":"2026-05-18T00:00:38.302959+00:00"}