{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WOBT7ZERJ7BOMCHNI4X2DFM65J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"667034cd8c40f05bffe3471d9ee0ea99bc39bf8d28caa17abb4bacf241f12ba6","cross_cats_sorted":["quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T10:54:53Z","title_canon_sha256":"e5300d707a92fb2cf7c0f25ec1b3486d8204b3be8fde4e82cef6b9d30b55c2b6"},"schema_version":"1.0","source":{"id":"2205.14988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14988","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14988v1","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14988","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"WOBT7ZERJ7BO","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"WOBT7ZERJ7BOMCHN","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"WOBT7ZER","created_at":"2026-07-05T04:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:6352ae3bba726cd09e3a1eb199c1e93dc854049c5cf47e26716ff50afdf51575","target":"graph","created_at":"2026-07-05T04:27:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.14988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jialin Zhang, Tongyang Li, Xiaoming Sun, Zhijie Zhang, Zongqi Wan","cross_cats":["quant-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T10:54:53Z","title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14988","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:22197881b9357466ed2a0fd6bfeb0ec1a1334612da1b20cc4b0ff4df6365b685","target":"record","created_at":"2026-07-05T04:27:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"667034cd8c40f05bffe3471d9ee0ea99bc39bf8d28caa17abb4bacf241f12ba6","cross_cats_sorted":["quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T10:54:53Z","title_canon_sha256":"e5300d707a92fb2cf7c0f25ec1b3486d8204b3be8fde4e82cef6b9d30b55c2b6"},"schema_version":"1.0","source":{"id":"2205.14988","kind":"arxiv","version":1}},"canonical_sha256":"b3833fe4914fc2e608ed472fa1959eea4946204e17800210d348fa8fe92df422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3833fe4914fc2e608ed472fa1959eea4946204e17800210d348fa8fe92df422","first_computed_at":"2026-07-05T04:27:23.287841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:23.287841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eMyrFyETySzhcZ5ClaQEHc2iPPC5AwzZ0iQs1mF39Sw+aIHbNvKxI/4LD4wSase0crrvbPkNjAmHBJBqlbghCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:23.288443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22197881b9357466ed2a0fd6bfeb0ec1a1334612da1b20cc4b0ff4df6365b685","sha256:6352ae3bba726cd09e3a1eb199c1e93dc854049c5cf47e26716ff50afdf51575"],"state_sha256":"342b14e5987fa0b0b1bfb94c129c2d023d52ecf85f9650d67592747e8a60311d"}