{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MYJO74CMZ366NHZN66HXI4ERVZ","short_pith_number":"pith:MYJO74CM","schema_version":"1.0","canonical_sha256":"6612eff04ccefde69f2df78f747091ae55172b5f348a5c34cbcb7637a9d96e39","source":{"kind":"arxiv","id":"2302.08617","version":1},"attestation_state":"computed","paper":{"title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhargav Ganguly, Di Wang, Vaneet Aggarwal, Yulian Wu","submitted_at":"2023-02-16T23:01:27Z","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 "},"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":"2302.08617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T23:01:27Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","quant-ph","stat.ML"],"title_canon_sha256":"51cad26b6f91a7afd6a92f95a02d5da7cfb98ef07a99a1468d3e574ffa9a5598","abstract_canon_sha256":"7747d0a6599e668d25eb1a21c8ce11851dd08d425a1451a9206fef66b74214f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:52.655054Z","signature_b64":"j4VH0O/vwviQVHj5rx03ujo3A8pzvoR4VZd20EFR/71Bh6geN+Q8vFVHQh1aYXgYKqb6CWFqcO/8OUAOtEWDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6612eff04ccefde69f2df78f747091ae55172b5f348a5c34cbcb7637a9d96e39","last_reissued_at":"2026-07-05T05:42:52.654642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:52.654642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhargav Ganguly, Di Wang, Vaneet Aggarwal, Yulian Wu","submitted_at":"2023-02-16T23:01:27Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08617","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/2302.08617/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":"2302.08617","created_at":"2026-07-05T05:42:52.654709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08617v1","created_at":"2026-07-05T05:42:52.654709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08617","created_at":"2026-07-05T05:42:52.654709+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYJO74CMZ366","created_at":"2026-07-05T05:42:52.654709+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYJO74CMZ366NHZN","created_at":"2026-07-05T05:42:52.654709+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYJO74CM","created_at":"2026-07-05T05:42:52.654709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01691","citing_title":"Quantum reinforcement learning in dynamic environments","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ","json":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ.json","graph_json":"https://pith.science/api/pith-number/MYJO74CMZ366NHZN66HXI4ERVZ/graph.json","events_json":"https://pith.science/api/pith-number/MYJO74CMZ366NHZN66HXI4ERVZ/events.json","paper":"https://pith.science/paper/MYJO74CM"},"agent_actions":{"view_html":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ","download_json":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ.json","view_paper":"https://pith.science/paper/MYJO74CM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08617&json=true","fetch_graph":"https://pith.science/api/pith-number/MYJO74CMZ366NHZN66HXI4ERVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MYJO74CMZ366NHZN66HXI4ERVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ/action/storage_attestation","attest_author":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ/action/author_attestation","sign_citation":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ/action/citation_signature","submit_replication":"https://pith.science/pith/MYJO74CMZ366NHZN66HXI4ERVZ/action/replication_record"}},"created_at":"2026-07-05T05:42:52.654709+00:00","updated_at":"2026-07-05T05:42:52.654709+00:00"}