{"id":"W2998388927","doi":"10.1109/access.2019.2961914","title":"Smart Power Control for Quality-Driven Multi-User Video Transmissions: A Deep Reinforcement Learning Approach","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; Division of Electrical, Communications and Cyber Systems; Auburn University; National Science Foundation","keywords":"Reinforcement learning; Computer science; Control (management); Quality (philosophy); Power control; Artificial intelligence; Power (physics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.001029454,0.0002611603,0.0004199274,0.0001301292,0.0002465438,0.0005959862,0.001639612,0.0001182158,0.00006764403],"category_scores_gemma":[0.00007402376,0.0002267788,0.0002315818,0.0002597384,0.00003316807,0.00171799,0.0001498142,0.0003088982,0.00008291375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000794996,"about_ca_system_score_gemma":0.0001319031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076175,"about_ca_topic_score_gemma":0.000009859773,"domain_scores_codex":[0.997387,0.0002861001,0.0006050984,0.0006684231,0.0004957305,0.0005576678],"domain_scores_gemma":[0.9982361,0.0003685186,0.0002468136,0.0007724279,0.0002087126,0.0001674007],"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":[0.0009593776,0.002972611,0.02882088,0.002403401,0.001301809,0.00003711076,0.02954343,0.7026451,0.02768499,0.1490079,0.007501486,0.04712197],"study_design_scores_gemma":[0.007288455,0.0003526539,0.003238882,0.0001026361,0.00004059231,0.000005567783,0.0003871704,0.9456862,0.003919879,0.0003884307,0.03780397,0.0007855685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005617428,0.00007579124,0.990004,0.0008836958,0.0005435484,0.001405121,0.000002238397,0.0001894088,0.001278758],"genre_scores_gemma":[0.9592297,0.000011355,0.0349783,0.002242652,0.00006201228,0.0002061009,0.00001172207,0.00002531031,0.003232832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550257,"threshold_uncertainty_score":0.9247772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05516992587832567,"score_gpt":0.3632557578432844,"score_spread":0.3080858319649588,"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."}}