{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MPF6ARRUEMF66UQ2JOWRI3ANBU","short_pith_number":"pith:MPF6ARRU","schema_version":"1.0","canonical_sha256":"63cbe04634230bef521a4bad146c0d0d3a95203b7289818c6b0e2fb8ccbbd6ab","source":{"kind":"arxiv","id":"2002.06772","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Bandit Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Chih-wei Hsu, Craig Boutilier, Csaba Szepesvari, Manzil Zaheer, Martin Mladenov","submitted_at":"2020-02-17T05:07:35Z","abstract_excerpt":"Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\\mathcal{P}$ using samples from $\\mathcal{P}$. Our approach is a form of meta-learning and exploits properties of $\\mathcal{P}$ without making strong assumptions about its form. To do this, we parameterize our policies in a differentiable way and optimize them by policy gradients, an approach that is general and easy to implement. We derive effective gradient estimators and introduce novel varia"},"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":"2002.06772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T05:07:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db95c23b34d739c7d8562751265742dfe4f5be5afb5a0622d850712d26804707","abstract_canon_sha256":"e7c93d9b9c795f8a7238c537749e9b44795970aa321aada3b5c3301dbde24870"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:03.774939Z","signature_b64":"oPzULd/ZGWNnr00I0QSPSDGmt+NKTw2gCfrCAoTT/gF9ZfvR+9uDuZll/Z/2iL1uY3HmcKGWF+t32V2GdsJtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63cbe04634230bef521a4bad146c0d0d3a95203b7289818c6b0e2fb8ccbbd6ab","last_reissued_at":"2026-07-05T01:09:03.774452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:03.774452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Bandit Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Chih-wei Hsu, Craig Boutilier, Csaba Szepesvari, Manzil Zaheer, Martin Mladenov","submitted_at":"2020-02-17T05:07:35Z","abstract_excerpt":"Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\\mathcal{P}$ using samples from $\\mathcal{P}$. Our approach is a form of meta-learning and exploits properties of $\\mathcal{P}$ without making strong assumptions about its form. To do this, we parameterize our policies in a differentiable way and optimize them by policy gradients, an approach that is general and easy to implement. We derive effective gradient estimators and introduce novel varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06772","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.06772/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":"2002.06772","created_at":"2026-07-05T01:09:03.774509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06772v2","created_at":"2026-07-05T01:09:03.774509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06772","created_at":"2026-07-05T01:09:03.774509+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPF6ARRUEMF6","created_at":"2026-07-05T01:09:03.774509+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPF6ARRUEMF66UQ2","created_at":"2026-07-05T01:09:03.774509+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPF6ARRU","created_at":"2026-07-05T01:09:03.774509+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/MPF6ARRUEMF66UQ2JOWRI3ANBU","json":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU.json","graph_json":"https://pith.science/api/pith-number/MPF6ARRUEMF66UQ2JOWRI3ANBU/graph.json","events_json":"https://pith.science/api/pith-number/MPF6ARRUEMF66UQ2JOWRI3ANBU/events.json","paper":"https://pith.science/paper/MPF6ARRU"},"agent_actions":{"view_html":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU","download_json":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU.json","view_paper":"https://pith.science/paper/MPF6ARRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06772&json=true","fetch_graph":"https://pith.science/api/pith-number/MPF6ARRUEMF66UQ2JOWRI3ANBU/graph.json","fetch_events":"https://pith.science/api/pith-number/MPF6ARRUEMF66UQ2JOWRI3ANBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU/action/storage_attestation","attest_author":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU/action/author_attestation","sign_citation":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU/action/citation_signature","submit_replication":"https://pith.science/pith/MPF6ARRUEMF66UQ2JOWRI3ANBU/action/replication_record"}},"created_at":"2026-07-05T01:09:03.774509+00:00","updated_at":"2026-07-05T01:09:03.774509+00:00"}