{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001138623,0.0002533183,0.0003181154,0.0002450039,0.0002879869,0.0007887878,0.001469808,0.00009303768,0.00006086119],"category_scores_gemma":[0.0003866476,0.0002213755,0.0001067042,0.0006346806,0.00001408668,0.0009767221,0.0003393845,0.0008947324,0.000553608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002161898,"about_ca_system_score_gemma":0.0002938946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003247775,"about_ca_topic_score_gemma":2.727388e-7,"domain_scores_codex":[0.997352,0.0001332799,0.0005526711,0.0003794606,0.0008958447,0.0006867201],"domain_scores_gemma":[0.9983295,0.000148778,0.0003808956,0.0004385388,0.000360386,0.0003419038],"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":[0.000008640446,0.00002862933,0.003816576,0.00006669356,0.00007920179,0.000008602614,0.004729819,0.9886008,0.0001800642,0.001373351,0.0002858137,0.0008218081],"study_design_scores_gemma":[0.001118433,0.0004892605,0.0005941306,0.00009198642,0.00002414759,0.0002772099,0.000333345,0.9857123,0.0001446111,0.00005785963,0.01080919,0.0003474725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004727904,0.00007124669,0.9750943,0.0005210634,0.0004517825,0.0004052233,2.54381e-8,0.0002185559,0.01850989],"genre_scores_gemma":[0.9214317,0.00003249938,0.07533312,0.0009769913,0.000204854,0.00001452373,9.862044e-7,0.00002524547,0.001980126],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9167038,"threshold_uncertainty_score":0.9027432,"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."}}