{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FI5J6NCE5YB3NUB4F7FQPFSVOW","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":"bec5444fee1de9f0aa57b318c9b65436621515793ce1b5b0e6f66fc667c0c6c1","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-02-21T16:23:11Z","title_canon_sha256":"dca2cdf3a25061e3853a64dc39f80704c655d729560e2284398393886871995d"},"schema_version":"1.0","source":{"id":"2302.10796","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10796","created_at":"2026-07-05T08:31:02Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10796v2","created_at":"2026-07-05T08:31:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10796","created_at":"2026-07-05T08:31:02Z"},{"alias_kind":"pith_short_12","alias_value":"FI5J6NCE5YB3","created_at":"2026-07-05T08:31:02Z"},{"alias_kind":"pith_short_16","alias_value":"FI5J6NCE5YB3NUB4","created_at":"2026-07-05T08:31:02Z"},{"alias_kind":"pith_short_8","alias_value":"FI5J6NCE","created_at":"2026-07-05T08:31:02Z"}],"graph_snapshots":[{"event_id":"sha256:3531fc57e357f4c58d7ffc730ea5e25d44eee6545d63a6fce18a88e9ec2141e8","target":"graph","created_at":"2026-07-05T08:31:02Z","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/2302.10796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Han Zhong, Jiachen Hu, Liwei Wang, Tongyang Li, Yecheng Xue","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-02-21T16:23:11Z","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10796","kind":"arxiv","version":2},"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":"sha256:5f69d27a4e7cec7d990bf227589fb2eb2c2577f2ff82986f8bdf66b79e2c9914","target":"record","created_at":"2026-07-05T08:31:02Z","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":"bec5444fee1de9f0aa57b318c9b65436621515793ce1b5b0e6f66fc667c0c6c1","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-02-21T16:23:11Z","title_canon_sha256":"dca2cdf3a25061e3853a64dc39f80704c655d729560e2284398393886871995d"},"schema_version":"1.0","source":{"id":"2302.10796","kind":"arxiv","version":2}},"canonical_sha256":"2a3a9f3444ee03b6d03c2fcb07965575895aa0be0d7db5d765dc066c42823c9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a3a9f3444ee03b6d03c2fcb07965575895aa0be0d7db5d765dc066c42823c9a","first_computed_at":"2026-07-05T08:31:02.686893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:02.686893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZR2X9VOPsfxZljwd4RxgnhmirrW9Ow3j7baO31WbW7X/2AfgXa+Sr5fStrWyfbnbE/hZtBnKv9/hU6NYng2KDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:02.687372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10796","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f69d27a4e7cec7d990bf227589fb2eb2c2577f2ff82986f8bdf66b79e2c9914","sha256:3531fc57e357f4c58d7ffc730ea5e25d44eee6545d63a6fce18a88e9ec2141e8"],"state_sha256":"a40ebe3d5d203156661915ca6187695fcff434fe55ef59e1b18a2c7c0523b530"}