{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002821565,0.0009228311,0.001385423,0.0006473239,0.0006442484,0.001368252,0.001793016,0.001385643,0.002820775],"category_scores_gemma":[0.01833576,0.0005789591,0.0005935099,0.0005040985,0.002257316,0.001902169,0.002160174,0.002284472,0.0003120298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001885571,"about_ca_system_score_gemma":0.0016479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005841013,"about_ca_topic_score_gemma":0.004898393,"domain_scores_codex":[0.9989533,0.0005039166,0.0000397615,0.0001410169,0.0002484603,0.0001134623],"domain_scores_gemma":[0.9934803,0.004876059,0.000475382,0.000310068,0.0005574367,0.0003007707],"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":[0.0000261136,0.00002296119,0.0005852628,0.00002670568,0.00002693113,0.00005554254,0.00003516832,0.9276141,0.0002326033,0.06270473,0.0004152732,0.008254674],"study_design_scores_gemma":[0.000003810717,0.000005105415,0.00002896909,0.000003205924,0.000001568468,0.000003442841,0.000001450237,0.983612,0.00005728216,0.01617477,0.0001061604,0.000002286523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02143037,0.0002474794,0.973696,0.0004558618,0.0000650497,0.00003174035,0.00002674308,0.0002075061,0.003839232],"genre_scores_gemma":[0.8376115,0.0002462278,0.1568772,0.0002895446,0.00008498432,0.0002119115,0.0001022814,0.0001492671,0.004427108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005841013,"threshold_uncertainty_score":0.01492202,"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."}}