{"id":"W4382652965","doi":"10.1002/9781119873747.ch3","title":"Deep Reinforcement Learning Models and Techniques","year":2023,"lang":"en","type":"other","venue":"","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Deep neural networks; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009481506,0.0009936946,0.0009511113,0.0005852763,0.0003377552,0.001578311,0.001491674,0.00137747,0.007241996],"category_scores_gemma":[0.002449585,0.0004607049,0.0006485018,0.0008270977,0.0009357909,0.001496934,0.001169957,0.002504124,0.001783367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001277437,"about_ca_system_score_gemma":0.0009904394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003824949,"about_ca_topic_score_gemma":0.003317598,"domain_scores_codex":[0.9995546,0.0001318823,0.00002645945,0.00009443846,0.0001412539,0.00005138449],"domain_scores_gemma":[0.9994565,0.0003188253,0.00005139434,0.00004507786,0.00009923993,0.00002905805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003538794,0.00006573177,0.0004575356,0.0002220348,0.00006048014,0.00007067609,0.000085038,0.4882675,0.0007460688,0.3990147,0.008147277,0.1028276],"study_design_scores_gemma":[0.00001170462,0.00002363263,0.00008421821,0.00005585547,0.00001165945,0.00003944688,0.00001173053,0.8131042,0.0003887542,0.1725566,0.01370024,0.00001190548],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.002518238,0.004891329,0.9697374,0.001309961,0.000179274,0.00004924391,0.0001776693,0.0003358773,0.02080092],"genre_scores_gemma":[0.5008029,0.01761024,0.4171579,0.001141359,0.0006849401,0.0006829931,0.0006865178,0.0003081032,0.06092513],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.007241996,"threshold_uncertainty_score":0.0242269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01894203960524971,"score_gpt":0.2598089280224286,"score_spread":0.2408668884171788,"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."}}