{"id":"W4360587554","doi":"10.2316/j.2023.201-0347","title":"REINFORCEMENT LEARNING: APPLICATION AND ADVANCES TOWARDS STABLE CONTROL STRATEGIES, 53-57. SI","year":2023,"lang":"en","type":"article","venue":"Mechatronic systems and control","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Control (management); Computer science; Artificial intelligence; Psychology; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001095154,0.0008244146,0.0006365033,0.0006300233,0.0003544542,0.002116896,0.0008453591,0.0009687837,0.01309163],"category_scores_gemma":[0.002828453,0.0003143292,0.0005598764,0.0007868152,0.0008790177,0.001443434,0.001060185,0.001700711,0.003493536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001034956,"about_ca_system_score_gemma":0.0008097273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002743564,"about_ca_topic_score_gemma":0.002515001,"domain_scores_codex":[0.9996001,0.0001107118,0.00002843922,0.00007500937,0.0001594396,0.00002628641],"domain_scores_gemma":[0.9994082,0.0003012582,0.00002891109,0.00006559812,0.0001740427,0.0000218687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001092167,0.0001633462,0.001040061,0.0006440089,0.00008337341,0.0001180067,0.000174923,0.08553659,0.006585757,0.1726195,0.01198946,0.7209357],"study_design_scores_gemma":[0.00004826516,0.0003388537,0.001965914,0.0002841498,0.000066786,0.0002759265,0.0001711358,0.7206306,0.01703875,0.1694705,0.08965108,0.0000579561],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01003712,0.01609119,0.9089761,0.001759109,0.0007985083,0.00008946873,0.0001872524,0.0007303715,0.06133084],"genre_scores_gemma":[0.5819326,0.02565695,0.3017695,0.000438487,0.0006118824,0.0002628393,0.0005298212,0.0003488775,0.08844901],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01309163,"threshold_uncertainty_score":0.04379582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009541579444280999,"score_gpt":0.2786455489871146,"score_spread":0.2691039695428336,"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."}}