{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AFYQOZXNJJAUPUI63RH72NY7Z3","short_pith_number":"pith:AFYQOZXN","schema_version":"1.0","canonical_sha256":"01710766ed4a4147d11edc4ffd371fceede59b947b1d731b599160b3e028de78","source":{"kind":"arxiv","id":"1902.02157","version":2},"attestation_state":"computed","paper":{"title":"When does reinforcement learning stand out in quantum control? A comparative study on state preparation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Raza Asad, Xiao-Ming Zhang, Xin Wang, Xu-Chen Yang, Zezhu Wei","submitted_at":"2019-02-06T13:18:35Z","abstract_excerpt":"Reinforcement learning has been widely used in many problems, including quantum control of qubits. However, such problems can, at the same time, be solved by traditional, non-machine-learning methods, such as stochastic gradient descent and Krotov algorithms, and it remains unclear which one is most suitable when the control has specific constraints. In this work, we perform a comparative study on the efficacy of three reinforcement learning algorithms: tabular Q-learning, deep Q-learning, and policy gradient, as well as two non-machine-learning methods: stochastic gradient descent and Krotov "},"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":"1902.02157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2019-02-06T13:18:35Z","cross_cats_sorted":[],"title_canon_sha256":"9787d7ebc4396ac49daaef06ab005c023175be7fd9589bf101dd3783d5f3b8ef","abstract_canon_sha256":"45fd8555dabf0ae6963f98a0155db37a1ce7d1a741329cb6590c0b4fe38828ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:39.731629Z","signature_b64":"z3jgEFEnIlVPcGdQKWIA7yjXIr+/uBflmcGlPr5kxtZjgGDoEAJtApuHSBIXYLe1PTosix7SqIX+cw3yHEnvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01710766ed4a4147d11edc4ffd371fceede59b947b1d731b599160b3e028de78","last_reissued_at":"2026-07-05T02:37:39.731212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:39.731212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When does reinforcement learning stand out in quantum control? A comparative study on state preparation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Raza Asad, Xiao-Ming Zhang, Xin Wang, Xu-Chen Yang, Zezhu Wei","submitted_at":"2019-02-06T13:18:35Z","abstract_excerpt":"Reinforcement learning has been widely used in many problems, including quantum control of qubits. However, such problems can, at the same time, be solved by traditional, non-machine-learning methods, such as stochastic gradient descent and Krotov algorithms, and it remains unclear which one is most suitable when the control has specific constraints. In this work, we perform a comparative study on the efficacy of three reinforcement learning algorithms: tabular Q-learning, deep Q-learning, and policy gradient, as well as two non-machine-learning methods: stochastic gradient descent and Krotov "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02157","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/1902.02157/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":"1902.02157","created_at":"2026-07-05T02:37:39.731272+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02157v2","created_at":"2026-07-05T02:37:39.731272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02157","created_at":"2026-07-05T02:37:39.731272+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFYQOZXNJJAU","created_at":"2026-07-05T02:37:39.731272+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFYQOZXNJJAUPUI6","created_at":"2026-07-05T02:37:39.731272+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFYQOZXN","created_at":"2026-07-05T02:37:39.731272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06283","citing_title":"Push-Pull Optimization of Quantum Controls","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3","json":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3.json","graph_json":"https://pith.science/api/pith-number/AFYQOZXNJJAUPUI63RH72NY7Z3/graph.json","events_json":"https://pith.science/api/pith-number/AFYQOZXNJJAUPUI63RH72NY7Z3/events.json","paper":"https://pith.science/paper/AFYQOZXN"},"agent_actions":{"view_html":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3","download_json":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3.json","view_paper":"https://pith.science/paper/AFYQOZXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02157&json=true","fetch_graph":"https://pith.science/api/pith-number/AFYQOZXNJJAUPUI63RH72NY7Z3/graph.json","fetch_events":"https://pith.science/api/pith-number/AFYQOZXNJJAUPUI63RH72NY7Z3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3/action/storage_attestation","attest_author":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3/action/author_attestation","sign_citation":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3/action/citation_signature","submit_replication":"https://pith.science/pith/AFYQOZXNJJAUPUI63RH72NY7Z3/action/replication_record"}},"created_at":"2026-07-05T02:37:39.731272+00:00","updated_at":"2026-07-05T02:37:39.731272+00:00"}