{"id":"W2761015455","doi":"10.1103/physrevx.8.031086","title":"Reinforcement Learning in Different Phases of Quantum Control","year":2018,"lang":"en","type":"article","venue":"Physical Review X","topic":"Quantum many-body systems","field":"Physics and Astronomy","cited_by":288,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Army Research Office; Division of Materials Research; Natural Sciences and Engineering Research Council of Canada; Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Air Force Office of Scientific Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Simons Foundation; National Science Foundation","keywords":"Reinforcement learning; Quantum; State (computer science); Quantum state; Control (management); Quantum computer","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001572652,0.0001595237,0.0006010322,0.00002899081,0.00003281625,0.000009098243,0.0001455176,0.000008972242,0.0003028275],"category_scores_gemma":[0.00003286013,0.0001150643,0.0001730083,0.000139399,0.00007145763,0.00006404286,0.00003778226,0.0001309896,0.0001173667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000179879,"about_ca_system_score_gemma":0.00002119361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001179002,"about_ca_topic_score_gemma":9.353453e-7,"domain_scores_codex":[0.9988777,0.0001097195,0.000398008,0.0001846485,0.0002050002,0.0002249407],"domain_scores_gemma":[0.9993088,0.0001226835,0.0002212249,0.0002260767,0.00006237565,0.00005888597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006389127,0.001172452,0.04132459,0.001902214,0.0002122442,0.000001877436,0.0005106093,0.0002028079,0.01476046,0.9168586,0.001361875,0.02162843],"study_design_scores_gemma":[0.009016736,0.003497904,0.0195431,0.02640444,0.0007346144,0.000001591464,0.0003694839,0.7752494,0.03134589,0.04869311,0.08311229,0.0020315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9801183,0.001723327,0.008592314,0.0002540871,0.0001364802,0.0007684131,0.000006365554,0.00002857848,0.008372181],"genre_scores_gemma":[0.9990929,0.00007212299,0.000002983258,0.00007343866,0.0005809027,0.00006715007,0.000008904019,0.00001227562,0.00008934034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8681654,"threshold_uncertainty_score":0.4692187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0157236703210432,"score_gpt":0.3133394669665215,"score_spread":0.2976157966454783,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}