{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GMSGTN6K5PGOFB26AQDXE7W6PY","short_pith_number":"pith:GMSGTN6K","schema_version":"1.0","canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","source":{"kind":"arxiv","id":"1604.00923","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Philip S. Thomas","submitted_at":"2016-04-04T15:56:52Z","abstract_excerpt":"In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important for applications where the deployment of a bad policy can be dangerous or costly. We show empirically that our algorithm produces estimates that often have orders of magnitude lower mean squared error than existing methods---it makes more efficient use of the available data. Our new estimator is based on two advances: an extension of the doubly robust estim"},"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":"1604.00923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-04T15:56:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2709d3c4c242f0ca0fd5bf5b32c55feaf8ee5feb0158baea80cdc1e4793ba580","abstract_canon_sha256":"9f8a1982bb1e482f59c99a737be072a38cf9e6e7e52472416e61e2f4ea2e402b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:47.785128Z","signature_b64":"OXRXNHxw9I27ePeZ2anOTS7vjQ4BHvxzaSbtuWWmRAabRo+eevcClNpqvzJ2bAcOpla2XFGBBmZgMd+MsYxHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","last_reissued_at":"2026-05-18T01:17:47.784325Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:47.784325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Philip S. Thomas","submitted_at":"2016-04-04T15:56:52Z","abstract_excerpt":"In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important for applications where the deployment of a bad policy can be dangerous or costly. We show empirically that our algorithm produces estimates that often have orders of magnitude lower mean squared error than existing methods---it makes more efficient use of the available data. Our new estimator is based on two advances: an extension of the doubly robust estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00923","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":"1604.00923","created_at":"2026-05-18T01:17:47.784450+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.00923v1","created_at":"2026-05-18T01:17:47.784450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00923","created_at":"2026-05-18T01:17:47.784450+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMSGTN6K5PGO","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMSGTN6K5PGOFB26","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMSGTN6K","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08441","citing_title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY","json":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY.json","graph_json":"https://pith.science/api/pith-number/GMSGTN6K5PGOFB26AQDXE7W6PY/graph.json","events_json":"https://pith.science/api/pith-number/GMSGTN6K5PGOFB26AQDXE7W6PY/events.json","paper":"https://pith.science/paper/GMSGTN6K"},"agent_actions":{"view_html":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY","download_json":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY.json","view_paper":"https://pith.science/paper/GMSGTN6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.00923&json=true","fetch_graph":"https://pith.science/api/pith-number/GMSGTN6K5PGOFB26AQDXE7W6PY/graph.json","fetch_events":"https://pith.science/api/pith-number/GMSGTN6K5PGOFB26AQDXE7W6PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/action/storage_attestation","attest_author":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/action/author_attestation","sign_citation":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/action/citation_signature","submit_replication":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/action/replication_record"}},"created_at":"2026-05-18T01:17:47.784450+00:00","updated_at":"2026-05-18T01:17:47.784450+00:00"}