{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:X3HGWP3BIERSORL57DDQ3KG4ZL","short_pith_number":"pith:X3HGWP3B","schema_version":"1.0","canonical_sha256":"bece6b3f61412327457df8c70da8dccae685ba531af53512849f8b51c86c68ac","source":{"kind":"arxiv","id":"1707.09727","version":1},"attestation_state":"computed","paper":{"title":"Taming Non-stationary Bandits: A Bayesian Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Sheetal Kalyani, Vishnu Raj","submitted_at":"2017-07-31T05:46:39Z","abstract_excerpt":"We consider the multi armed bandit problem in non-stationary environments. Based on the Bayesian method, we propose a variant of Thompson Sampling which can be used in both rested and restless bandit scenarios. Applying discounting to the parameters of prior distribution, we describe a way to systematically reduce the effect of past observations. Further, we derive the exact expression for the probability of picking sub-optimal arms. By increasing the exploitative value of Bayes' samples, we also provide an optimistic version of the algorithm. Extensive empirical analysis is conducted under va"},"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":"1707.09727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-31T05:46:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e884f7857d90b726a9c30e1816790292018ad149e2020b540916e36235ac3ce","abstract_canon_sha256":"22ebdeac9459bee0bcfa74cb53c951fbf9da5dcd5e65204041831a723f89df8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:08.448407Z","signature_b64":"9AY2tcHbRzxK3wJBZYNI1hc83SNBxM/yfUanfl/sERuDhdZL2ehJb89irECP3LgIC/mjdD8GxrutIG13p9N7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bece6b3f61412327457df8c70da8dccae685ba531af53512849f8b51c86c68ac","last_reissued_at":"2026-05-18T00:39:08.447735Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:08.447735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming Non-stationary Bandits: A Bayesian Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Sheetal Kalyani, Vishnu Raj","submitted_at":"2017-07-31T05:46:39Z","abstract_excerpt":"We consider the multi armed bandit problem in non-stationary environments. Based on the Bayesian method, we propose a variant of Thompson Sampling which can be used in both rested and restless bandit scenarios. Applying discounting to the parameters of prior distribution, we describe a way to systematically reduce the effect of past observations. Further, we derive the exact expression for the probability of picking sub-optimal arms. By increasing the exploitative value of Bayes' samples, we also provide an optimistic version of the algorithm. Extensive empirical analysis is conducted under va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09727","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":"1707.09727","created_at":"2026-05-18T00:39:08.447840+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09727v1","created_at":"2026-05-18T00:39:08.447840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09727","created_at":"2026-05-18T00:39:08.447840+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3HGWP3BIERS","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3HGWP3BIERSORL5","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3HGWP3B","created_at":"2026-05-18T12:31:53.515858+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/X3HGWP3BIERSORL57DDQ3KG4ZL","json":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL.json","graph_json":"https://pith.science/api/pith-number/X3HGWP3BIERSORL57DDQ3KG4ZL/graph.json","events_json":"https://pith.science/api/pith-number/X3HGWP3BIERSORL57DDQ3KG4ZL/events.json","paper":"https://pith.science/paper/X3HGWP3B"},"agent_actions":{"view_html":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL","download_json":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL.json","view_paper":"https://pith.science/paper/X3HGWP3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09727&json=true","fetch_graph":"https://pith.science/api/pith-number/X3HGWP3BIERSORL57DDQ3KG4ZL/graph.json","fetch_events":"https://pith.science/api/pith-number/X3HGWP3BIERSORL57DDQ3KG4ZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL/action/storage_attestation","attest_author":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL/action/author_attestation","sign_citation":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL/action/citation_signature","submit_replication":"https://pith.science/pith/X3HGWP3BIERSORL57DDQ3KG4ZL/action/replication_record"}},"created_at":"2026-05-18T00:39:08.447840+00:00","updated_at":"2026-05-18T00:39:08.447840+00:00"}