{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QSSDBHCTVG2IFN3EVAYJBY37D5","short_pith_number":"pith:QSSDBHCT","schema_version":"1.0","canonical_sha256":"84a4309c53a9b482b764a83090e37f1f51a78ead057f4cb100925093f34b0306","source":{"kind":"arxiv","id":"2202.00821","version":3},"attestation_state":"computed","paper":{"title":"Optimizing Sequential Experimental Design with Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Dezfouli, Edwin V. Bonilla, Iadine Chades, Tom Blau","submitted_at":"2022-02-02T00:23:05Z","abstract_excerpt":"Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches practical, by training a parameterized policy that proposes designs efficiently at deployment time. However, these methods may not sufficiently explore the design space, require access to a differentiable probabilistic model and can only optimize over continuous design spaces. Here, we address these limitations by showing that the problem of optimizing policies"},"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":"2202.00821","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-02T00:23:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"42c789e14d60dfb9842876be2040da5de37124f30d04ca2ddc8d0855b5a9e0a9","abstract_canon_sha256":"f3e44389d35b44afd8b1d130c017c819109754ec8635481fd333a1b76ac96659"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:38.906730Z","signature_b64":"WRm9A3mbfdTZ3xKZIzssebtr9wKf7nFwVSs9Xki60rWfLm9l3I0NsCnLxHTOkQv83pmUKFIZVxZktnm2A9jwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84a4309c53a9b482b764a83090e37f1f51a78ead057f4cb100925093f34b0306","last_reissued_at":"2026-07-05T04:32:38.906254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:38.906254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Sequential Experimental Design with Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Dezfouli, Edwin V. Bonilla, Iadine Chades, Tom Blau","submitted_at":"2022-02-02T00:23:05Z","abstract_excerpt":"Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches practical, by training a parameterized policy that proposes designs efficiently at deployment time. However, these methods may not sufficiently explore the design space, require access to a differentiable probabilistic model and can only optimize over continuous design spaces. Here, we address these limitations by showing that the problem of optimizing policies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00821","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/2202.00821/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":"2202.00821","created_at":"2026-07-05T04:32:38.906310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00821v3","created_at":"2026-07-05T04:32:38.906310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00821","created_at":"2026-07-05T04:32:38.906310+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSSDBHCTVG2I","created_at":"2026-07-05T04:32:38.906310+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSSDBHCTVG2IFN3E","created_at":"2026-07-05T04:32:38.906310+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSSDBHCT","created_at":"2026-07-05T04:32:38.906310+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/QSSDBHCTVG2IFN3EVAYJBY37D5","json":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5.json","graph_json":"https://pith.science/api/pith-number/QSSDBHCTVG2IFN3EVAYJBY37D5/graph.json","events_json":"https://pith.science/api/pith-number/QSSDBHCTVG2IFN3EVAYJBY37D5/events.json","paper":"https://pith.science/paper/QSSDBHCT"},"agent_actions":{"view_html":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5","download_json":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5.json","view_paper":"https://pith.science/paper/QSSDBHCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00821&json=true","fetch_graph":"https://pith.science/api/pith-number/QSSDBHCTVG2IFN3EVAYJBY37D5/graph.json","fetch_events":"https://pith.science/api/pith-number/QSSDBHCTVG2IFN3EVAYJBY37D5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5/action/storage_attestation","attest_author":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5/action/author_attestation","sign_citation":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5/action/citation_signature","submit_replication":"https://pith.science/pith/QSSDBHCTVG2IFN3EVAYJBY37D5/action/replication_record"}},"created_at":"2026-07-05T04:32:38.906310+00:00","updated_at":"2026-07-05T04:32:38.906310+00:00"}