{"id":"W4406135959","doi":"10.1088/2632-2153/ada71d","title":"A reinforcement learning approach to the design of quantum chains for optimal energy and state transfer","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Spectroscopy and Quantum Chemical Studies","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"HORIZON EUROPE European Innovation Council; HORIZON EUROPE Framework Programme; Queen's University; Queen's University Belfast; Royal Society; Engineering and Physical Sciences Research Council; Leverhulme Trust; Department for the Economy","keywords":"Reinforcement learning; Markov chain; Chain (unit); Excitation; Markov decision process; Computer science; Mathematical optimization; Quantum; Optimal design; Q-learning; Markov process; Statistical physics; Physics; Mathematics; Quantum mechanics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001504079,0.0006946864,0.0009709395,0.0005054759,0.0005320576,0.0007425235,0.001079479,0.001150335,0.00252038],"category_scores_gemma":[0.004002295,0.000538819,0.0004546389,0.0002829981,0.001717382,0.0007204466,0.001105672,0.001091862,0.00027002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001285881,"about_ca_system_score_gemma":0.001517993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002919903,"about_ca_topic_score_gemma":0.002333249,"domain_scores_codex":[0.9994979,0.0001998501,0.00002146315,0.00009140698,0.0001098516,0.00007948774],"domain_scores_gemma":[0.9979568,0.001293553,0.0002190682,0.0001153451,0.0002770534,0.0001383094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001984782,0.00002389063,0.0001203017,0.00002156109,0.000008803344,0.00002416483,0.00002038394,0.9851775,0.001070167,0.007885742,0.00009970641,0.005527952],"study_design_scores_gemma":[0.000006861736,0.00001575419,0.00001201288,0.000002864251,0.000001663011,0.000002443335,0.000001789079,0.9973971,0.0001999814,0.002266191,0.00009137391,0.000002052953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02085327,0.0001017801,0.9766061,0.0001708696,0.00001815119,0.00006694444,0.00001383187,0.0001152019,0.00205385],"genre_scores_gemma":[0.8434007,0.0001289231,0.1538417,0.0001004277,0.00002531348,0.000262155,0.00003282312,0.00004807316,0.002159859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002919903,"threshold_uncertainty_score":0.009329736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009277254475842508,"score_gpt":0.2495382329383942,"score_spread":0.2402609784625517,"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."}}