{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3VHZZBNVNVVAJZPPR2AYJLX5II","short_pith_number":"pith:3VHZZBNV","schema_version":"1.0","canonical_sha256":"dd4f9c85b56d6a04e5ef8e8184aefd423c853b791dc37c89f0fadcf0d0bcd513","source":{"kind":"arxiv","id":"1911.06854","version":3},"attestation_state":"computed","paper":{"title":"Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Voloshin, Hoang M. Le, Nan Jiang, Yisong Yue","submitted_at":"2019-11-15T19:58:42Z","abstract_excerpt":"We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there has been a flurry of recent proposals for OPE method, leading to a need for standardized empirical analyses. Our work takes a strong focus on diversity of experimental design to enable stress testing of OPE methods. We provide a comprehensive benchmarking suite to study the interplay of different attributes on method performance. We distill th"},"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":"1911.06854","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-15T19:58:42Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"2c83b3af97c29cc90f56ea9f066911e06c2a433437384378e2c83ccf6838eb51","abstract_canon_sha256":"9bfed4c59893b4bccf78b11d5daf92951310c4b25e9fc760542133b656ecb8ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:25.082920Z","signature_b64":"dYD6IjdPOaf/ahxsE5ParlkcYZgSsLv6DP91LkVnTsUWXoKx1c1zbBWk+QnJXDLbR3rDhZAteugXGqbrcBE0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd4f9c85b56d6a04e5ef8e8184aefd423c853b791dc37c89f0fadcf0d0bcd513","last_reissued_at":"2026-07-05T03:35:25.082421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:25.082421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Voloshin, Hoang M. Le, Nan Jiang, Yisong Yue","submitted_at":"2019-11-15T19:58:42Z","abstract_excerpt":"We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there has been a flurry of recent proposals for OPE method, leading to a need for standardized empirical analyses. Our work takes a strong focus on diversity of experimental design to enable stress testing of OPE methods. We provide a comprehensive benchmarking suite to study the interplay of different attributes on method performance. We distill th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06854","kind":"arxiv","version":3},"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/1911.06854/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":"1911.06854","created_at":"2026-07-05T03:35:25.082492+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06854v3","created_at":"2026-07-05T03:35:25.082492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06854","created_at":"2026-07-05T03:35:25.082492+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VHZZBNVNVVA","created_at":"2026-07-05T03:35:25.082492+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VHZZBNVNVVAJZPP","created_at":"2026-07-05T03:35:25.082492+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VHZZBNV","created_at":"2026-07-05T03:35:25.082492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05375","citing_title":"Fitted Occupancy-Ratio Evaluation without Bellman Completeness","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20206","citing_title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05558","citing_title":"Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01028","citing_title":"MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II","json":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II.json","graph_json":"https://pith.science/api/pith-number/3VHZZBNVNVVAJZPPR2AYJLX5II/graph.json","events_json":"https://pith.science/api/pith-number/3VHZZBNVNVVAJZPPR2AYJLX5II/events.json","paper":"https://pith.science/paper/3VHZZBNV"},"agent_actions":{"view_html":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II","download_json":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II.json","view_paper":"https://pith.science/paper/3VHZZBNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06854&json=true","fetch_graph":"https://pith.science/api/pith-number/3VHZZBNVNVVAJZPPR2AYJLX5II/graph.json","fetch_events":"https://pith.science/api/pith-number/3VHZZBNVNVVAJZPPR2AYJLX5II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II/action/storage_attestation","attest_author":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II/action/author_attestation","sign_citation":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II/action/citation_signature","submit_replication":"https://pith.science/pith/3VHZZBNVNVVAJZPPR2AYJLX5II/action/replication_record"}},"created_at":"2026-07-05T03:35:25.082492+00:00","updated_at":"2026-07-05T03:35:25.082492+00:00"}