{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001524003,0.0001443985,0.0001477865,0.0001919366,0.00005268514,0.00009733115,0.0003121925,0.0001223151,0.0001559775],"category_scores_gemma":[0.0000146116,0.0001203538,0.00002799391,0.0001179144,0.00001546459,0.00007607351,0.0003229167,0.0001811813,0.0001164312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000011464,"about_ca_system_score_gemma":0.00001146698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007168899,"about_ca_topic_score_gemma":0.000092783,"domain_scores_codex":[0.9992417,0.00002745582,0.00009835212,0.0002976213,0.0001600598,0.0001748357],"domain_scores_gemma":[0.9995646,0.00002473585,0.00006998571,0.0002800576,0.000008965965,0.0000516382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.665045e-7,0.00000810141,0.00003091407,0.00007220011,0.00004471233,0.0000166595,0.0003646878,0.01174239,0.000002510126,0.1416626,0.3188854,0.527169],"study_design_scores_gemma":[0.00003620182,0.00003340685,0.000001611456,0.0000586133,0.000002349632,0.000002598385,0.000004202697,0.5403376,0.00000708948,0.0008084776,0.4585649,0.000142934],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[9.765282e-8,0.00008386777,0.5021991,0.000104479,0.00004474825,0.00004964728,1.906443e-8,0.002900987,0.4946171],"genre_scores_gemma":[0.0005820994,0.0003816085,0.03408008,0.0001249822,0.00008218439,0.00001576962,0.000001655496,0.000223927,0.9645077],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5285952,"threshold_uncertainty_score":0.4907887,"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."}}