{"id":"W2955319481","doi":"10.1002/aic.16689","title":"Toward self‐driving processes: A deep reinforcement learning approach to control","year":2019,"lang":"en","type":"article","venue":"AIChE Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Self driving; Reinforcement; Self-control; Control (management); Computer science; Artificial intelligence; Engineering; Psychology; Social psychology; Transport engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000731565,0.0004913674,0.0005017924,0.0002520024,0.0002458165,0.0005431129,0.0008532794,0.0007312971,0.001347165],"category_scores_gemma":[0.001522035,0.0002533119,0.0003192291,0.0002047978,0.0009241971,0.0005611267,0.0007718704,0.001238964,0.000131033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008092059,"about_ca_system_score_gemma":0.0007485403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005890329,"about_ca_topic_score_gemma":0.004054972,"domain_scores_codex":[0.9998074,0.00006686417,0.000008103092,0.00003369843,0.00005380239,0.00003018547],"domain_scores_gemma":[0.9994763,0.0002724335,0.00006976323,0.00004004003,0.000108743,0.00003271926],"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":[0.0000119764,0.00001860102,0.000185559,0.00001511714,0.00001107465,0.00001649265,0.00001874131,0.9805617,0.0008845752,0.008834914,0.0001897331,0.00925148],"study_design_scores_gemma":[0.000001712991,0.000005428817,0.00001531612,9.659152e-7,8.788135e-7,0.0000012041,6.947328e-7,0.9983663,0.00007373533,0.001463133,0.00006990894,7.906e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02387824,0.000200081,0.9720256,0.0003063627,0.00002852698,0.00002496858,0.0000138605,0.0001966041,0.003325677],"genre_scores_gemma":[0.9386797,0.0001581877,0.05854211,0.0001106962,0.0000326995,0.00006692056,0.00001926551,0.00002789685,0.002362489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005890329,"threshold_uncertainty_score":0.01171213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01407432987377703,"score_gpt":0.2322518334943767,"score_spread":0.2181775036205997,"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."}}