{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FI5J6NCE5YB3NUB4F7FQPFSVOW","short_pith_number":"pith:FI5J6NCE","schema_version":"1.0","canonical_sha256":"2a3a9f3444ee03b6d03c2fcb07965575895aa0be0d7db5d765dc066c42823c9a","source":{"kind":"arxiv","id":"2302.10796","version":2},"attestation_state":"computed","paper":{"title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Han Zhong, Jiachen Hu, Liwei Wang, Tongyang Li, Yecheng Xue","submitted_at":"2023-02-21T16:23:11Z","abstract_excerpt":"While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is limited. In particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the exploration-exploitation trade-off. To this end, we propose a novel UCRL-style algorithm that takes advantage of quantum computing for tabular Markov decision processes (MDPs) with $S$ states, $A$ actions, and horizon $H$, and establish an $\\mathcal{O}(\\mathrm{poly}(S, A, H, \\log T))$ worst-case regret for it, where $T$ is the number of episodes. Furthermore,"},"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":"2302.10796","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-02-21T16:23:11Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"dca2cdf3a25061e3853a64dc39f80704c655d729560e2284398393886871995d","abstract_canon_sha256":"bec5444fee1de9f0aa57b318c9b65436621515793ce1b5b0e6f66fc667c0c6c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:02.687372Z","signature_b64":"ZR2X9VOPsfxZljwd4RxgnhmirrW9Ow3j7baO31WbW7X/2AfgXa+Sr5fStrWyfbnbE/hZtBnKv9/hU6NYng2KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a3a9f3444ee03b6d03c2fcb07965575895aa0be0d7db5d765dc066c42823c9a","last_reissued_at":"2026-07-05T08:31:02.686893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:02.686893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Han Zhong, Jiachen Hu, Liwei Wang, Tongyang Li, Yecheng Xue","submitted_at":"2023-02-21T16:23:11Z","abstract_excerpt":"While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is limited. In particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the exploration-exploitation trade-off. To this end, we propose a novel UCRL-style algorithm that takes advantage of quantum computing for tabular Markov decision processes (MDPs) with $S$ states, $A$ actions, and horizon $H$, and establish an $\\mathcal{O}(\\mathrm{poly}(S, A, H, \\log T))$ worst-case regret for it, where $T$ is the number of episodes. Furthermore,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10796","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.10796/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":"2302.10796","created_at":"2026-07-05T08:31:02.686954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10796v2","created_at":"2026-07-05T08:31:02.686954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10796","created_at":"2026-07-05T08:31:02.686954+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI5J6NCE5YB3","created_at":"2026-07-05T08:31:02.686954+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI5J6NCE5YB3NUB4","created_at":"2026-07-05T08:31:02.686954+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI5J6NCE","created_at":"2026-07-05T08:31:02.686954+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":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW","json":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW.json","graph_json":"https://pith.science/api/pith-number/FI5J6NCE5YB3NUB4F7FQPFSVOW/graph.json","events_json":"https://pith.science/api/pith-number/FI5J6NCE5YB3NUB4F7FQPFSVOW/events.json","paper":"https://pith.science/paper/FI5J6NCE"},"agent_actions":{"view_html":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW","download_json":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW.json","view_paper":"https://pith.science/paper/FI5J6NCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10796&json=true","fetch_graph":"https://pith.science/api/pith-number/FI5J6NCE5YB3NUB4F7FQPFSVOW/graph.json","fetch_events":"https://pith.science/api/pith-number/FI5J6NCE5YB3NUB4F7FQPFSVOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW/action/storage_attestation","attest_author":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW/action/author_attestation","sign_citation":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW/action/citation_signature","submit_replication":"https://pith.science/pith/FI5J6NCE5YB3NUB4F7FQPFSVOW/action/replication_record"}},"created_at":"2026-07-05T08:31:02.686954+00:00","updated_at":"2026-07-05T08:31:02.686954+00:00"}