{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4OOBHC7TEVSENAM4GFY6DKHTES","short_pith_number":"pith:4OOBHC7T","schema_version":"1.0","canonical_sha256":"e39c138bf3256446819c3171e1a8f324a3b5b407ae144f397fc0cb855d789d8e","source":{"kind":"arxiv","id":"1710.02869","version":2},"attestation_state":"computed","paper":{"title":"An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Isaac J. Sledge, Jose C. Principe","submitted_at":"2017-10-08T18:48:48Z","abstract_excerpt":"In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of policy information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We dem"},"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":"1710.02869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-08T18:48:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0c8aa39bb3c14cf25b9ed7790f09e02e9dc3292b8f61e18b32ead1a12d6ddf8c","abstract_canon_sha256":"07d57ce4522facc720734e2f21a0756c4e41a31375735af47260d26d6afffc64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:05.609095Z","signature_b64":"onIUvVTEMahvdEXwxLVFfCiQ7/jw1XWXln+Qd5pNNdNJPr1hpPn84zLuGrz0Nt2coYo2EEwN9eUMLvzCG5x8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e39c138bf3256446819c3171e1a8f324a3b5b407ae144f397fc0cb855d789d8e","last_reissued_at":"2026-05-18T00:22:05.608483Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:05.608483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Isaac J. Sledge, Jose C. Principe","submitted_at":"2017-10-08T18:48:48Z","abstract_excerpt":"In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of policy information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We dem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02869","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":""},"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":"1710.02869","created_at":"2026-05-18T00:22:05.608571+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.02869v2","created_at":"2026-05-18T00:22:05.608571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02869","created_at":"2026-05-18T00:22:05.608571+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OOBHC7TEVSE","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OOBHC7TEVSENAM4","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OOBHC7T","created_at":"2026-05-18T12:31:00.734936+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/4OOBHC7TEVSENAM4GFY6DKHTES","json":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES.json","graph_json":"https://pith.science/api/pith-number/4OOBHC7TEVSENAM4GFY6DKHTES/graph.json","events_json":"https://pith.science/api/pith-number/4OOBHC7TEVSENAM4GFY6DKHTES/events.json","paper":"https://pith.science/paper/4OOBHC7T"},"agent_actions":{"view_html":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES","download_json":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES.json","view_paper":"https://pith.science/paper/4OOBHC7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.02869&json=true","fetch_graph":"https://pith.science/api/pith-number/4OOBHC7TEVSENAM4GFY6DKHTES/graph.json","fetch_events":"https://pith.science/api/pith-number/4OOBHC7TEVSENAM4GFY6DKHTES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES/action/storage_attestation","attest_author":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES/action/author_attestation","sign_citation":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES/action/citation_signature","submit_replication":"https://pith.science/pith/4OOBHC7TEVSENAM4GFY6DKHTES/action/replication_record"}},"created_at":"2026-05-18T00:22:05.608571+00:00","updated_at":"2026-05-18T00:22:05.608571+00:00"}