{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TUF7WCOG72N5T7XECCSPR2XWEO","short_pith_number":"pith:TUF7WCOG","schema_version":"1.0","canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","source":{"kind":"arxiv","id":"1903.08738","version":1},"attestation_state":"computed","paper":{"title":"Batch Policy Learning under Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Voloshin, Hoang M. Le, Yisong Yue","submitted_at":"2019-03-20T21:01:22Z","abstract_excerpt":"When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We thus study the problem of batch policy learning under multiple constraints, and offer a systematic solution. We first propose a flexible meta-algorithm that admits any batch reinforcement learning and online learning procedure as subroutines. We then present a specific algorithmic instantiation and provide performance guarantees for the main objective and all"},"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":"1903.08738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T21:01:22Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"f32354d3d6a08122ec85fe7cf86e77587e1df65e70e469060b308da099d1ebdb","abstract_canon_sha256":"7c9938a879e8515c100d8fb7ad496d46d452c7f3e6549c66734309166448766d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:44.066662Z","signature_b64":"CZsDnHXjSBFHPKD0NcimmvXRpb5Dh2DXAVucF8IH6xyPhrNoIs9hFlDDbw7HRc/hM8saJ4/22UEmycIUXpP+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d0bfb09c6fe9bd9fee410a4f8eaf6239dae4eddbedc2e99a78795e86f092f25","last_reissued_at":"2026-05-17T23:50:44.066138Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:44.066138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Batch Policy Learning under Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Voloshin, Hoang M. Le, Yisong Yue","submitted_at":"2019-03-20T21:01:22Z","abstract_excerpt":"When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We thus study the problem of batch policy learning under multiple constraints, and offer a systematic solution. We first propose a flexible meta-algorithm that admits any batch reinforcement learning and online learning procedure as subroutines. We then present a specific algorithmic instantiation and provide performance guarantees for the main objective and all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08738","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":"1903.08738","created_at":"2026-05-17T23:50:44.066220+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08738v1","created_at":"2026-05-17T23:50:44.066220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08738","created_at":"2026-05-17T23:50:44.066220+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUF7WCOG72N5","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUF7WCOG72N5T7XE","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUF7WCOG","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO","json":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO.json","graph_json":"https://pith.science/api/pith-number/TUF7WCOG72N5T7XECCSPR2XWEO/graph.json","events_json":"https://pith.science/api/pith-number/TUF7WCOG72N5T7XECCSPR2XWEO/events.json","paper":"https://pith.science/paper/TUF7WCOG"},"agent_actions":{"view_html":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO","download_json":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO.json","view_paper":"https://pith.science/paper/TUF7WCOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08738&json=true","fetch_graph":"https://pith.science/api/pith-number/TUF7WCOG72N5T7XECCSPR2XWEO/graph.json","fetch_events":"https://pith.science/api/pith-number/TUF7WCOG72N5T7XECCSPR2XWEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/action/storage_attestation","attest_author":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/action/author_attestation","sign_citation":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/action/citation_signature","submit_replication":"https://pith.science/pith/TUF7WCOG72N5T7XECCSPR2XWEO/action/replication_record"}},"created_at":"2026-05-17T23:50:44.066220+00:00","updated_at":"2026-05-17T23:50:44.066220+00:00"}