{"id":"W4387478892","doi":"10.2316/j.2023.201-0371","title":"RESEARCH PROGRESS ABOUT DEEP REINFORCEMENT LEARNING, 210-217. SI","year":2023,"lang":"en","type":"article","venue":"Mechatronic systems and control","topic":"Advanced Sensor and Control Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Machine learning; Turing; Artificial neural network; Deep learning","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":[0.001264648,0.0002700894,0.0004996994,0.000267631,0.0003218321,0.0001862927,0.0002100553,0.0001663008,0.00002292291],"category_scores_gemma":[0.0000363448,0.0002402861,0.00009391153,0.0004071954,0.00006483021,0.0001458903,0.00004504127,0.0004726651,0.0002720475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001626967,"about_ca_system_score_gemma":0.00002708769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009998211,"about_ca_topic_score_gemma":0.00002577762,"domain_scores_codex":[0.9972858,0.0002096571,0.000495916,0.000362979,0.0006133474,0.001032295],"domain_scores_gemma":[0.9990555,0.0001716318,0.00006650334,0.0003739891,0.0001348561,0.0001975097],"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":[0.0001033192,0.00001964611,0.001604661,0.0008393947,0.0004957987,0.00009389569,0.001040601,0.9289618,0.004376404,0.02747617,0.001347028,0.03364129],"study_design_scores_gemma":[0.002255853,0.0001945368,0.0003634718,0.0001447486,0.00002811172,0.00002294091,0.002150971,0.9178514,0.00006223955,0.000133429,0.07647513,0.0003171285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2650208,0.2560861,0.3989708,0.0008902255,0.009923963,0.01324717,0.00004040395,0.01109995,0.04472065],"genre_scores_gemma":[0.9944093,0.0004710422,0.000005733453,0.00001080829,0.000520985,0.0006378653,0.00001251182,0.00007417701,0.003857582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7293885,"threshold_uncertainty_score":0.9798582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396246987320863,"score_gpt":0.2655993845823718,"score_spread":0.2516369147091631,"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."}}