{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001456811,0.0001495951,0.0003120659,0.00008361744,0.0006525276,0.0002702622,0.0001142545,0.0001088329,0.0000243987],"category_scores_gemma":[0.00006802527,0.0001323991,0.00004275554,0.0002156657,0.00007826173,0.0003902251,0.00002319504,0.000185612,0.00002459441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007599917,"about_ca_system_score_gemma":0.0003700486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002184867,"about_ca_topic_score_gemma":0.0004818384,"domain_scores_codex":[0.9982952,0.000250679,0.0002834067,0.0003105155,0.0003616538,0.0004985532],"domain_scores_gemma":[0.9993465,0.0001292439,0.0001742327,0.0001271829,0.00008648547,0.000136336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001791352,0.00004416124,0.005949745,0.0003590135,0.0002708488,0.00001271423,0.004179017,0.04669224,0.002305046,0.6039994,0.0003398394,0.3356688],"study_design_scores_gemma":[0.002288823,0.0002130863,0.0003195597,0.0000463932,0.00006960347,0.00000232068,0.04162368,0.08375278,0.000009395056,0.00107232,0.8703457,0.0002563792],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2531426,0.1090198,0.5337318,0.01358154,0.002709446,0.009601656,0.00006724928,0.002824476,0.07532146],"genre_scores_gemma":[0.9941567,0.001823116,0.00001982242,0.00004020476,0.0004234679,0.0001968699,0.00001228643,0.00001426839,0.00331327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8700058,"threshold_uncertainty_score":0.5399078,"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."}}