{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R63OJYP3D6TCPJIIQBPFQKYA7W","short_pith_number":"pith:R63OJYP3","schema_version":"1.0","canonical_sha256":"8fb6e4e1fb1fa627a508805e582b00fdb2d2bed2593d689a7a85c32c4851a0ac","source":{"kind":"arxiv","id":"1901.08708","version":2},"attestation_state":"computed","paper":{"title":"Almost Boltzmann Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harsh Gupta, R. Srikant, Seo Taek Kong, Weina Wang","submitted_at":"2019-01-25T01:29:24Z","abstract_excerpt":"Boltzmann exploration is widely used in reinforcement learning to provide a trade-off between exploration and exploitation. Recently, in (Cesa-Bianchi et al., 2017) it has been shown that pure Boltzmann exploration does not perform well from a regret perspective, even in the simplest setting of stochastic multi-armed bandit (MAB) problems. In this paper, we show that a simple modification to Boltzmann exploration, motivated by a variation of the standard doubling trick, achieves $O(K\\log^{1+\\alpha} T)$ regret for a stochastic MAB problem with $K$ arms, where $\\alpha>0$ is a parameter of the al"},"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":"1901.08708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T01:29:24Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"fd6852e5b8b9474fa460031f426d82062518d133646794141273cd80f0bce563","abstract_canon_sha256":"2148c01e3b59d00680bca240415fea51e713610c6454f77377a94438edf55c34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:07.524947Z","signature_b64":"gPKuWRdRmhnOLkV7fEPwzHtiiZD2h3D2QnA0PL1v0kqwr7XklqkiO2U7TBWtNzc17wgCkCcqf3xAH54V9al5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fb6e4e1fb1fa627a508805e582b00fdb2d2bed2593d689a7a85c32c4851a0ac","last_reissued_at":"2026-05-17T23:48:07.524389Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:07.524389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Almost Boltzmann Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harsh Gupta, R. Srikant, Seo Taek Kong, Weina Wang","submitted_at":"2019-01-25T01:29:24Z","abstract_excerpt":"Boltzmann exploration is widely used in reinforcement learning to provide a trade-off between exploration and exploitation. Recently, in (Cesa-Bianchi et al., 2017) it has been shown that pure Boltzmann exploration does not perform well from a regret perspective, even in the simplest setting of stochastic multi-armed bandit (MAB) problems. In this paper, we show that a simple modification to Boltzmann exploration, motivated by a variation of the standard doubling trick, achieves $O(K\\log^{1+\\alpha} T)$ regret for a stochastic MAB problem with $K$ arms, where $\\alpha>0$ is a parameter of the al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08708","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":"1901.08708","created_at":"2026-05-17T23:48:07.524488+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08708v2","created_at":"2026-05-17T23:48:07.524488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08708","created_at":"2026-05-17T23:48:07.524488+00:00"},{"alias_kind":"pith_short_12","alias_value":"R63OJYP3D6TC","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"R63OJYP3D6TCPJII","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"R63OJYP3","created_at":"2026-05-18T12:33:27.125529+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/R63OJYP3D6TCPJIIQBPFQKYA7W","json":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W.json","graph_json":"https://pith.science/api/pith-number/R63OJYP3D6TCPJIIQBPFQKYA7W/graph.json","events_json":"https://pith.science/api/pith-number/R63OJYP3D6TCPJIIQBPFQKYA7W/events.json","paper":"https://pith.science/paper/R63OJYP3"},"agent_actions":{"view_html":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W","download_json":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W.json","view_paper":"https://pith.science/paper/R63OJYP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08708&json=true","fetch_graph":"https://pith.science/api/pith-number/R63OJYP3D6TCPJIIQBPFQKYA7W/graph.json","fetch_events":"https://pith.science/api/pith-number/R63OJYP3D6TCPJIIQBPFQKYA7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W/action/storage_attestation","attest_author":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W/action/author_attestation","sign_citation":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W/action/citation_signature","submit_replication":"https://pith.science/pith/R63OJYP3D6TCPJIIQBPFQKYA7W/action/replication_record"}},"created_at":"2026-05-17T23:48:07.524488+00:00","updated_at":"2026-05-17T23:48:07.524488+00:00"}