{"id":"W3091989295","doi":"10.1109/pimrc48278.2020.9217381","title":"Learning in the Sky: Towards Efficient 3D Placement of UAVs","year":2020,"lang":"en","type":"article","venue":"","topic":"UAV Applications and Optimization","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Software deployment; Reinforcement learning; Computer science; Leverage (statistics); Base station; Distributed computing; Benchmark (surveying); Throughput; Telecommunications link; Real-time computing; Wireless; Computer network; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006165123,0.00003100449,0.00003880986,0.0000138382,0.00001130772,0.00000601982,0.00005448712,0.00001263779,0.00008700138],"category_scores_gemma":[0.000006774372,0.00002222977,0.000009676251,0.0001548452,0.000004317031,0.000008857465,0.000008875776,0.00004980328,0.00001203873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009488652,"about_ca_system_score_gemma":0.000003989793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008959828,"about_ca_topic_score_gemma":0.000002207576,"domain_scores_codex":[0.9997565,0.000006826444,0.00008356934,0.0000419361,0.00006249334,0.00004867369],"domain_scores_gemma":[0.9999137,0.00001050634,0.000007848227,0.00004939168,0.000007877099,0.0000106654],"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":[9.557534e-7,0.000007222035,0.00009135865,0.000009674296,0.000001835024,8.065539e-8,0.001242654,0.9954303,0.0002934875,0.0005041866,0.0001774112,0.002240861],"study_design_scores_gemma":[0.00009034171,0.00001784347,0.0008193802,0.000002294443,0.000002158623,1.093487e-7,0.0004889053,0.9927948,0.001023736,0.000001908794,0.004729117,0.00002936737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3010733,0.00009566361,0.6146187,0.001466884,0.00003230757,0.0003218511,0.000001479871,0.0001776698,0.08221221],"genre_scores_gemma":[0.9971436,0.00001491434,0.002707327,0.00007371767,0.00001152087,0.00001355319,0.000003637638,0.000004425666,0.0000273347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6960703,"threshold_uncertainty_score":0.0952604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009522283048383021,"score_gpt":0.2024823467100953,"score_spread":0.1929600636617123,"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."}}