{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XMWWJ3WE7YHZDGTQU7NWTXBFX3","short_pith_number":"pith:XMWWJ3WE","schema_version":"1.0","canonical_sha256":"bb2d64eec4fe0f919a70a7db69dc25bee0b6614e6fd6048fb6794fadc54f5a98","source":{"kind":"arxiv","id":"1910.07186","version":1},"attestation_state":"computed","paper":{"title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dengyong Zhou, Lihong Li, Qiang Liu, Yihao Feng, Ziyang Tang","submitted_at":"2019-10-16T06:33:17Z","abstract_excerpt":"Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al. (2018a) proposed an approach that significantly reduces the variance of infinite-horizon off-policy evaluation by estimating the stationary density ratio, but at the cost of introducing potentially high biases due to the error in density ratio estimation. In this paper, we develop a bias-reduced augmentation of their method, which can take advantage of a learned value function to obtain higher accuracy. Our method "},"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":"1910.07186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-16T06:33:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f10ffae7604975311511b58d00a81da39e73fe70c5bb9b8774846a0af1d9c38c","abstract_canon_sha256":"c55c0072154ac613bb705e989060e30fc4071bd8a337433c4d9eadd2e16ceabb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:33.623594Z","signature_b64":"VGslYeGvk5RxDMe+ECFLK21Zr5l3tEFoYhaqz6ISwy/YW/udk6YpomwnozCKHJGeQMoDl5BHnnOvoze2WnKKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2d64eec4fe0f919a70a7db69dc25bee0b6614e6fd6048fb6794fadc54f5a98","last_reissued_at":"2026-07-05T00:12:33.623147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:33.623147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dengyong Zhou, Lihong Li, Qiang Liu, Yihao Feng, Ziyang Tang","submitted_at":"2019-10-16T06:33:17Z","abstract_excerpt":"Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al. (2018a) proposed an approach that significantly reduces the variance of infinite-horizon off-policy evaluation by estimating the stationary density ratio, but at the cost of introducing potentially high biases due to the error in density ratio estimation. In this paper, we develop a bias-reduced augmentation of their method, which can take advantage of a learned value function to obtain higher accuracy. Our method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07186","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/1910.07186/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1910.07186","created_at":"2026-07-05T00:12:33.623212+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.07186v1","created_at":"2026-07-05T00:12:33.623212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07186","created_at":"2026-07-05T00:12:33.623212+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMWWJ3WE7YHZ","created_at":"2026-07-05T00:12:33.623212+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMWWJ3WE7YHZDGTQ","created_at":"2026-07-05T00:12:33.623212+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMWWJ3WE","created_at":"2026-07-05T00:12:33.623212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":262,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3","json":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3.json","graph_json":"https://pith.science/api/pith-number/XMWWJ3WE7YHZDGTQU7NWTXBFX3/graph.json","events_json":"https://pith.science/api/pith-number/XMWWJ3WE7YHZDGTQU7NWTXBFX3/events.json","paper":"https://pith.science/paper/XMWWJ3WE"},"agent_actions":{"view_html":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3","download_json":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3.json","view_paper":"https://pith.science/paper/XMWWJ3WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.07186&json=true","fetch_graph":"https://pith.science/api/pith-number/XMWWJ3WE7YHZDGTQU7NWTXBFX3/graph.json","fetch_events":"https://pith.science/api/pith-number/XMWWJ3WE7YHZDGTQU7NWTXBFX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3/action/storage_attestation","attest_author":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3/action/author_attestation","sign_citation":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3/action/citation_signature","submit_replication":"https://pith.science/pith/XMWWJ3WE7YHZDGTQU7NWTXBFX3/action/replication_record"}},"created_at":"2026-07-05T00:12:33.623212+00:00","updated_at":"2026-07-05T00:12:33.623212+00:00"}