{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:C5K4B3XGX56QIFQ3HQJJU77NBB","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":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8"},"schema_version":"1.0","source":{"id":"1811.06225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06225","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06225v1","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06225","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"C5K4B3XGX56Q","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C5K4B3XGX56QIFQ3","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C5K4B3XG","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:52b845e86676c94aaf16ece4ee2905fea6eacdede0d546fe94556af5781b0f7a","target":"graph","created_at":"2026-05-18T00:00:38Z","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"},"paper":{"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","authors_text":"Sergey Pankov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","title":"Reward-estimation variance elimination in sequential decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06225","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":"sha256:9277893fbabb841afd6044b508f99f1ddd5499a883a29206fceb4284dfb3dd91","target":"record","created_at":"2026-05-18T00:00:38Z","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":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8"},"schema_version":"1.0","source":{"id":"1811.06225","kind":"arxiv","version":1}},"canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","first_computed_at":"2026-05-18T00:00:38.302890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:38.302890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d4EMc16Q6nkUxSuXoiHqJF/xq5NUaWXoEV78A27OjjJW5jGQVCYqgOcWjRU6QPiptV7Y6Lx2mw96DtrjyjuWAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:38.303345Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.06225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9277893fbabb841afd6044b508f99f1ddd5499a883a29206fceb4284dfb3dd91","sha256:52b845e86676c94aaf16ece4ee2905fea6eacdede0d546fe94556af5781b0f7a"],"state_sha256":"a988640527704e7cf8a686fcd4b59978ef236eb3fe113d16a2e3a1d5e0c64084"}