{"id":"W2738109916","doi":"10.1109/adconip.2017.7983780","title":"Deep reinforcement learning approaches for process control","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Process (computing); Controller (irrigation); Artificial neural network; Process control; Control (management); Artificial intelligence; Control system; Control engineering; Function (biology); Deep learning; Control theory (sociology); MIMO; Engineering; Channel (broadcasting)","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":[0.0004448445,0.0001574064,0.0001824826,0.00005417621,0.0009779142,0.000840867,0.001754096,0.0000629116,0.00002786817],"category_scores_gemma":[0.0004124763,0.0001348024,0.00008312708,0.00004058638,0.0000634754,0.0008750503,0.0002097895,0.0001532778,0.00004735761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003298042,"about_ca_system_score_gemma":0.0000504732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007207171,"about_ca_topic_score_gemma":0.000001794894,"domain_scores_codex":[0.9986842,0.00002056788,0.0002518641,0.0003405335,0.0003020117,0.0004008046],"domain_scores_gemma":[0.9985043,0.00009934389,0.000319231,0.0008708144,0.0001148608,0.00009139458],"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":[0.000008090954,0.000006679224,0.001193602,0.00003128855,0.0000252756,7.909434e-7,0.0002880701,0.925234,0.000006447061,0.06479172,0.00006363242,0.008350421],"study_design_scores_gemma":[0.0009857106,0.0001726643,0.0004783247,0.00001130496,0.00000944029,0.0000021686,0.00006169959,0.9950585,0.0002578341,0.0005769857,0.002192732,0.0001926156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001529556,0.0000113598,0.9618305,0.0008147518,0.0002084577,0.0005197524,3.761568e-8,0.0002057317,0.03625648],"genre_scores_gemma":[0.9657788,0.000002606724,0.0272948,0.0001971481,0.00008331164,0.0001135543,0.000002704023,0.00001307282,0.006514054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9656258,"threshold_uncertainty_score":0.81085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04951332030694924,"score_gpt":0.2817894084133649,"score_spread":0.2322760881064156,"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."}}