{"id":"W2971992878","doi":"10.1063/5.0015301","title":"Evolutionary reinforcement learning of dynamical large deviations","year":2020,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Advanced Thermodynamics and Statistical Mechanics","field":"Physics and Astronomy","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada); National Research Council Canada; Vector Institute","funders":"Basic Energy Sciences; Lawrence Berkeley National Laboratory; Office of Science; U.S. Department of Energy","keywords":"Reinforcement learning; Path (computing); Trajectory; Computer science; Process (computing); Artificial neural network; Monte Carlo method; State (computer science); Function (biology); Large deviations theory; Statistical physics; Artificial intelligence; Mathematical optimization; Mathematics; Algorithm; Physics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000891069,0.00008125776,0.0001871729,0.000006428365,0.00004549768,0.000004159809,0.0001790127,0.00001825014,0.00007805538],"category_scores_gemma":[0.00004011812,0.00005725286,0.0001087807,0.0001093675,0.00004041408,0.00006626625,0.00006557904,0.0003462421,0.000004248522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002007912,"about_ca_system_score_gemma":0.00003879573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001184045,"about_ca_topic_score_gemma":8.157975e-9,"domain_scores_codex":[0.9992426,0.00003400646,0.0003297427,0.00005022345,0.0002141929,0.0001292557],"domain_scores_gemma":[0.9992346,0.0001631967,0.0003091239,0.00007004492,0.0001386982,0.00008435422],"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":[0.000110276,0.0001272775,0.0001899685,0.00001707459,0.0001170067,6.620483e-7,0.0004050397,0.01975434,0.09726988,0.8794508,0.0001677069,0.002389984],"study_design_scores_gemma":[0.0007803374,0.0001958307,0.00007299949,0.0000383814,0.0001313565,0.000001852204,0.0003015717,0.6224605,0.01649263,0.3588018,0.000574587,0.0001482114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07543846,0.00003312559,0.9234567,0.0003122928,0.00002978018,0.00004335281,0.00001677264,0.000003780811,0.0006657539],"genre_scores_gemma":[0.9985376,0.00000716291,0.001086977,0.00006794433,0.0002691135,5.984877e-7,0.00001236609,0.000009774854,0.000008469976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9230991,"threshold_uncertainty_score":0.2334704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009990062885032002,"score_gpt":0.2458874094870408,"score_spread":0.2358973466020088,"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."}}