{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WOBT7ZERJ7BOMCHNI4X2DFM65J","short_pith_number":"pith:WOBT7ZER","schema_version":"1.0","canonical_sha256":"b3833fe4914fc2e608ed472fa1959eea4946204e17800210d348fa8fe92df422","source":{"kind":"arxiv","id":"2205.14988","version":1},"attestation_state":"computed","paper":{"title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph"],"primary_cat":"cs.LG","authors_text":"Jialin Zhang, Tongyang Li, Xiaoming Sun, Zhijie Zhang, Zongqi Wan","submitted_at":"2022-05-30T10:54:53Z","abstract_excerpt":"Multi-arm bandit (MAB) and stochastic linear bandit (SLB) are important models in reinforcement learning, and it is well-known that classical algorithms for bandits with time horizon $T$ suffer $\\Omega(\\sqrt{T})$ regret. In this paper, we study MAB and SLB with quantum reward oracles and propose quantum algorithms for both models with $O(\\mbox{poly}(\\log T))$ regrets, exponentially improving the dependence in terms of $T$. To the best of our knowledge, this is the first provable quantum speedup for regrets of bandit problems and in general exploitation in reinforcement learning. Compared to pr"},"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":"2205.14988","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T10:54:53Z","cross_cats_sorted":["quant-ph"],"title_canon_sha256":"e5300d707a92fb2cf7c0f25ec1b3486d8204b3be8fde4e82cef6b9d30b55c2b6","abstract_canon_sha256":"667034cd8c40f05bffe3471d9ee0ea99bc39bf8d28caa17abb4bacf241f12ba6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:23.288443Z","signature_b64":"eMyrFyETySzhcZ5ClaQEHc2iPPC5AwzZ0iQs1mF39Sw+aIHbNvKxI/4LD4wSase0crrvbPkNjAmHBJBqlbghCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3833fe4914fc2e608ed472fa1959eea4946204e17800210d348fa8fe92df422","last_reissued_at":"2026-07-05T04:27:23.287841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:23.287841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph"],"primary_cat":"cs.LG","authors_text":"Jialin Zhang, Tongyang Li, Xiaoming Sun, Zhijie Zhang, Zongqi Wan","submitted_at":"2022-05-30T10:54:53Z","abstract_excerpt":"Multi-arm bandit (MAB) and stochastic linear bandit (SLB) are important models in reinforcement learning, and it is well-known that classical algorithms for bandits with time horizon $T$ suffer $\\Omega(\\sqrt{T})$ regret. In this paper, we study MAB and SLB with quantum reward oracles and propose quantum algorithms for both models with $O(\\mbox{poly}(\\log T))$ regrets, exponentially improving the dependence in terms of $T$. To the best of our knowledge, this is the first provable quantum speedup for regrets of bandit problems and in general exploitation in reinforcement learning. Compared to pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14988","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.14988/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":"2205.14988","created_at":"2026-07-05T04:27:23.287890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14988v1","created_at":"2026-07-05T04:27:23.287890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14988","created_at":"2026-07-05T04:27:23.287890+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOBT7ZERJ7BO","created_at":"2026-07-05T04:27:23.287890+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOBT7ZERJ7BOMCHN","created_at":"2026-07-05T04:27:23.287890+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOBT7ZER","created_at":"2026-07-05T04:27:23.287890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04438","citing_title":"Quantum Algorithms for Bandits with Knapsacks with Improved Regret and Time Complexities","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J","json":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J.json","graph_json":"https://pith.science/api/pith-number/WOBT7ZERJ7BOMCHNI4X2DFM65J/graph.json","events_json":"https://pith.science/api/pith-number/WOBT7ZERJ7BOMCHNI4X2DFM65J/events.json","paper":"https://pith.science/paper/WOBT7ZER"},"agent_actions":{"view_html":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J","download_json":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J.json","view_paper":"https://pith.science/paper/WOBT7ZER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14988&json=true","fetch_graph":"https://pith.science/api/pith-number/WOBT7ZERJ7BOMCHNI4X2DFM65J/graph.json","fetch_events":"https://pith.science/api/pith-number/WOBT7ZERJ7BOMCHNI4X2DFM65J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J/action/storage_attestation","attest_author":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J/action/author_attestation","sign_citation":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J/action/citation_signature","submit_replication":"https://pith.science/pith/WOBT7ZERJ7BOMCHNI4X2DFM65J/action/replication_record"}},"created_at":"2026-07-05T04:27:23.287890+00:00","updated_at":"2026-07-05T04:27:23.287890+00:00"}