{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:RRO5C75LZ63BS5QGPCBKJYBT4B","short_pith_number":"pith:RRO5C75L","schema_version":"1.0","canonical_sha256":"8c5dd17fabcfb61976067882a4e033e0764f1ea67a73e7d919b70e550ca08d2d","source":{"kind":"arxiv","id":"1402.6028","version":1},"attestation_state":"computed","paper":{"title":"Algorithms for multi-armed bandit problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Doina Precup, Volodymyr Kuleshov","submitted_at":"2014-02-25T01:34:43Z","abstract_excerpt":"Although many algorithms for the multi-armed bandit problem are well-understood theoretically, empirical confirmation of their effectiveness is generally scarce. This paper presents a thorough empirical study of the most popular multi-armed bandit algorithms. Three important observations can be made from our results. Firstly, simple heuristics such as epsilon-greedy and Boltzmann exploration outperform theoretically sound algorithms on most settings by a significant margin. Secondly, the performance of most algorithms varies dramatically with the parameters of the bandit problem. Our study ide"},"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":"1402.6028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-02-25T01:34:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00aa2ac772a0ef4af64a1629c82868a7ea142d1c4ddbf65da1fb2f0630210c12","abstract_canon_sha256":"377dca83cb2e946bcc31e76a3a03ef9232bc7ff72c0dc023747a0e217eb63202"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:57:51.829948Z","signature_b64":"SUiy8I1Ylbc2URNlpF0aABengQjNyczI1gtxUeC3fUr6kflSAkYbM6H9RcXvhWybiRGmTnWqUHRK7dxfPnOzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c5dd17fabcfb61976067882a4e033e0764f1ea67a73e7d919b70e550ca08d2d","last_reissued_at":"2026-05-18T02:57:51.829444Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:57:51.829444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithms for multi-armed bandit problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Doina Precup, Volodymyr Kuleshov","submitted_at":"2014-02-25T01:34:43Z","abstract_excerpt":"Although many algorithms for the multi-armed bandit problem are well-understood theoretically, empirical confirmation of their effectiveness is generally scarce. This paper presents a thorough empirical study of the most popular multi-armed bandit algorithms. Three important observations can be made from our results. Firstly, simple heuristics such as epsilon-greedy and Boltzmann exploration outperform theoretically sound algorithms on most settings by a significant margin. Secondly, the performance of most algorithms varies dramatically with the parameters of the bandit problem. Our study ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.6028","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":"1402.6028","created_at":"2026-05-18T02:57:51.829520+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.6028v1","created_at":"2026-05-18T02:57:51.829520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.6028","created_at":"2026-05-18T02:57:51.829520+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRO5C75LZ63B","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRO5C75LZ63BS5QG","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRO5C75L","created_at":"2026-05-18T12:28:46.137349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08208","citing_title":"Exploring Exploration in Bayesian Optimization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06296","citing_title":"AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B","json":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B.json","graph_json":"https://pith.science/api/pith-number/RRO5C75LZ63BS5QGPCBKJYBT4B/graph.json","events_json":"https://pith.science/api/pith-number/RRO5C75LZ63BS5QGPCBKJYBT4B/events.json","paper":"https://pith.science/paper/RRO5C75L"},"agent_actions":{"view_html":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B","download_json":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B.json","view_paper":"https://pith.science/paper/RRO5C75L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.6028&json=true","fetch_graph":"https://pith.science/api/pith-number/RRO5C75LZ63BS5QGPCBKJYBT4B/graph.json","fetch_events":"https://pith.science/api/pith-number/RRO5C75LZ63BS5QGPCBKJYBT4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B/action/storage_attestation","attest_author":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B/action/author_attestation","sign_citation":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B/action/citation_signature","submit_replication":"https://pith.science/pith/RRO5C75LZ63BS5QGPCBKJYBT4B/action/replication_record"}},"created_at":"2026-05-18T02:57:51.829520+00:00","updated_at":"2026-05-18T02:57:51.829520+00:00"}