{"id":"W4382653350","doi":"10.1002/9781119873747.ch1","title":"Deep Reinforcement Learning and Its Applications","year":2023,"lang":"en","type":"other","venue":"","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Reinforcement learning; Computer science; Data science; Artificial intelligence","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":[0.0005971225,0.0007010518,0.0006102766,0.0004190601,0.0002542887,0.001322126,0.0005741483,0.0008671903,0.006672499],"category_scores_gemma":[0.001504876,0.0002924725,0.0004175559,0.0007078406,0.0005708277,0.0009800288,0.001029845,0.00192758,0.002085973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009950451,"about_ca_system_score_gemma":0.0006329686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002510908,"about_ca_topic_score_gemma":0.001949724,"domain_scores_codex":[0.9997198,0.00006717896,0.00001320999,0.00006132403,0.0001111094,0.00002732174],"domain_scores_gemma":[0.9996717,0.0001890011,0.00001573527,0.00002706545,0.00007320333,0.00002334938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005065213,0.00008576537,0.0006933729,0.0005160467,0.0000538746,0.0001034006,0.0001092693,0.1933158,0.002492376,0.201071,0.03117691,0.5703316],"study_design_scores_gemma":[0.00001033658,0.00006436768,0.0004510597,0.0002182957,0.00001661456,0.000129958,0.00003974236,0.6713485,0.001967344,0.2084641,0.1172628,0.00002703954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00868142,0.07656229,0.7782266,0.004773814,0.001225089,0.00006336501,0.0003867213,0.001470939,0.1286098],"genre_scores_gemma":[0.4556483,0.121292,0.2931258,0.001804105,0.002026809,0.0002830459,0.0009592164,0.0006150544,0.1242457],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006672499,"threshold_uncertainty_score":0.02232176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007289158701237019,"score_gpt":0.2285564089983202,"score_spread":0.2212672502970832,"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."}}