{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z2XRN42N254OSJKQTS2SN7X6VA","short_pith_number":"pith:Z2XRN42N","schema_version":"1.0","canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","source":{"kind":"arxiv","id":"1802.03493","version":2},"attestation_state":"computed","paper":{"title":"More Robust Doubly Robust Off-policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mehrdad Farajtabar, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2018-02-10T01:32:03Z","abstract_excerpt":"We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time. Although the accuracy of the model has a huge impact on the overall performance of DR, most of the work on using the DR estimators in OPE has been focused on improving the IS part, "},"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":"1802.03493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:32:03Z","cross_cats_sorted":[],"title_canon_sha256":"86a4ae1339d9ea158370f88afcc3db475f43c072e6b52d82ba7d497e5443549f","abstract_canon_sha256":"96a4ea45a6f67d33dd101da440908a1ec728547ecff4ac47b8c573b806d7b56b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:04.972870Z","signature_b64":"940bcyZXK2zKyYXsgvFi7fDm3DAlkWfEHgZADb+voA75RzzJyuo+tCGwpQ+A66py37La3ThDCxoRxVWvSE10Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","last_reissued_at":"2026-05-18T00:15:04.972252Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:04.972252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Robust Doubly Robust Off-policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mehrdad Farajtabar, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2018-02-10T01:32:03Z","abstract_excerpt":"We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time. Although the accuracy of the model has a huge impact on the overall performance of DR, most of the work on using the DR estimators in OPE has been focused on improving the IS part, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03493","kind":"arxiv","version":2},"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":"1802.03493","created_at":"2026-05-18T00:15:04.972348+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03493v2","created_at":"2026-05-18T00:15:04.972348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03493","created_at":"2026-05-18T00:15:04.972348+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2XRN42N254O","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2XRN42N254OSJKQ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2XRN42N","created_at":"2026-05-18T12:33:04.347982+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":298,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA","json":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA.json","graph_json":"https://pith.science/api/pith-number/Z2XRN42N254OSJKQTS2SN7X6VA/graph.json","events_json":"https://pith.science/api/pith-number/Z2XRN42N254OSJKQTS2SN7X6VA/events.json","paper":"https://pith.science/paper/Z2XRN42N"},"agent_actions":{"view_html":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA","download_json":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA.json","view_paper":"https://pith.science/paper/Z2XRN42N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03493&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2XRN42N254OSJKQTS2SN7X6VA/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2XRN42N254OSJKQTS2SN7X6VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/action/storage_attestation","attest_author":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/action/author_attestation","sign_citation":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/action/citation_signature","submit_replication":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/action/replication_record"}},"created_at":"2026-05-18T00:15:04.972348+00:00","updated_at":"2026-05-18T00:15:04.972348+00:00"}