{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004058304,0.00009543091,0.0001581646,0.000155551,0.0005230835,0.00002610535,0.0001736143,0.00002420391,0.000002457718],"category_scores_gemma":[0.00006616311,0.0000645099,0.00001708105,0.0005991923,0.0004458368,0.00003665941,0.0001227421,0.0001607841,1.246284e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001022404,"about_ca_system_score_gemma":0.00003861968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001176513,"about_ca_topic_score_gemma":0.000001265164,"domain_scores_codex":[0.9992716,0.00001646967,0.0001285714,0.0002429168,0.00009088535,0.0002495627],"domain_scores_gemma":[0.9997246,0.00007443036,0.00002872107,0.00008245206,0.0000645538,0.00002520756],"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":[0.00007331568,0.00004943134,0.006768208,0.0000258765,0.00005938428,1.246959e-7,0.0009155494,0.04746891,0.04845697,0.8576185,0.00005946782,0.03850432],"study_design_scores_gemma":[0.0005830227,0.0006053243,0.0001594392,0.00002886668,0.00003045303,8.024081e-7,0.001358899,0.8977692,0.08060883,0.008747061,0.009936869,0.000171216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830294,0.0001832864,0.814522,0.001468546,0.00001662769,0.0001646646,0.000001378074,0.00003022373,0.0005838668],"genre_scores_gemma":[0.998231,0.00002394892,0.001235049,0.0000551837,0.00000887329,0.00007960398,0.000001651726,0.000003949719,0.0003607725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8503003,"threshold_uncertainty_score":0.4023188,"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."}}