{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MYJO74CMZ366NHZN66HXI4ERVZ","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":"7747d0a6599e668d25eb1a21c8ce11851dd08d425a1451a9206fef66b74214f4","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","quant-ph","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T23:01:27Z","title_canon_sha256":"51cad26b6f91a7afd6a92f95a02d5da7cfb98ef07a99a1468d3e574ffa9a5598"},"schema_version":"1.0","source":{"id":"2302.08617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08617","created_at":"2026-07-05T05:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08617v1","created_at":"2026-07-05T05:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08617","created_at":"2026-07-05T05:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"MYJO74CMZ366","created_at":"2026-07-05T05:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"MYJO74CMZ366NHZN","created_at":"2026-07-05T05:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"MYJO74CM","created_at":"2026-07-05T05:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:2d1f407d4cfb73b4c2569f768a27e7b550771bf65d6e402edc9356eb6961ce5f","target":"graph","created_at":"2026-07-05T05:42:52Z","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/2302.08617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate the problem of \\textit{episodic reinforcement learning} with quantum oracles for state evolution. To this end, we propose an \\textit{Upper Confidence Bound} (UCB) based quantum algorithmic framework to facilitate learning of a finite-horizon MDP. Our quantum algorithm achieves an exponential improvement in regret as compared to the classical counterparts, achieving a regret of $\\Tilde{\\mathcal{O}}(1)$ as compared to $\\Tilde{\\mathcal{O}}(\\sqrt{K})$ \\footnote{$\\Tilde{\\mathcal{O}}(\\cdot)$ hides logarithmic terms.}, $K$ being the number of training episodes. In order ","authors_text":"Bhargav Ganguly, Di Wang, Vaneet Aggarwal, Yulian Wu","cross_cats":["cs.AI","cs.SY","eess.SY","quant-ph","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T23:01:27Z","title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08617","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":"sha256:3dba4bf6cc931d86a6f8ec8b035d5f065a85c6257460d227736cf018d10c1826","target":"record","created_at":"2026-07-05T05:42:52Z","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":"7747d0a6599e668d25eb1a21c8ce11851dd08d425a1451a9206fef66b74214f4","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","quant-ph","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T23:01:27Z","title_canon_sha256":"51cad26b6f91a7afd6a92f95a02d5da7cfb98ef07a99a1468d3e574ffa9a5598"},"schema_version":"1.0","source":{"id":"2302.08617","kind":"arxiv","version":1}},"canonical_sha256":"6612eff04ccefde69f2df78f747091ae55172b5f348a5c34cbcb7637a9d96e39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6612eff04ccefde69f2df78f747091ae55172b5f348a5c34cbcb7637a9d96e39","first_computed_at":"2026-07-05T05:42:52.654642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:52.654642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j4VH0O/vwviQVHj5rx03ujo3A8pzvoR4VZd20EFR/71Bh6geN+Q8vFVHQh1aYXgYKqb6CWFqcO/8OUAOtEWDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:52.655054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dba4bf6cc931d86a6f8ec8b035d5f065a85c6257460d227736cf018d10c1826","sha256:2d1f407d4cfb73b4c2569f768a27e7b550771bf65d6e402edc9356eb6961ce5f"],"state_sha256":"3cf994f7068ec8fc0b33c05afecdfa8eb9ae4271c32b7a9c5c3e8a0b4b7bd8e2"}