{"id":"W4286481976","doi":"10.48550/arxiv.1906.09550","title":"Reinforcement Learning-Based Trajectory Design for the Aerial Base\\n Stations","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"UAV Applications and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Trajectory; Base station; Computer science; Network topology; Channel (broadcasting); Mathematical optimization; Information exchange; Trajectory optimization; Base (topology); Power (physics); Artificial intelligence; Optimal control; Computer network; Mathematics; Telecommunications","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":[0.0007159308,0.0007152314,0.0006323885,0.0002974859,0.0003953573,0.0004943914,0.000906964,0.0008394251,0.002634678],"category_scores_gemma":[0.001831944,0.0003023352,0.0003538543,0.0002759408,0.0007982771,0.0007051844,0.0007899383,0.001073084,0.00031597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009897117,"about_ca_system_score_gemma":0.001254814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008231658,"about_ca_topic_score_gemma":0.00513781,"domain_scores_codex":[0.9996831,0.00009937317,0.00001329608,0.00007984135,0.00006180503,0.00006246711],"domain_scores_gemma":[0.9993314,0.0003185362,0.0001075602,0.00003606149,0.0001427743,0.00006383343],"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":[0.0000442399,0.00001904538,0.0002451469,0.00002383984,0.000009918647,0.00003675881,0.00002585124,0.9821983,0.0007016321,0.004354614,0.0002936001,0.01204708],"study_design_scores_gemma":[0.000007302416,0.00002550296,0.00003165993,0.000002675218,0.000002341177,0.000005275728,0.000005139351,0.9982626,0.0001678254,0.001280452,0.0002076203,0.000001662398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01716158,0.0001544857,0.9799446,0.0001921214,0.00003127825,0.00004908746,0.00002706571,0.0001340335,0.002305621],"genre_scores_gemma":[0.9218478,0.0001780769,0.07391192,0.00009603303,0.00002257213,0.0001483554,0.0000712929,0.00003409266,0.003689746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008231658,"threshold_uncertainty_score":0.0163675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06836415485363867,"score_gpt":0.1802759379439195,"score_spread":0.1119117830902808,"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."}}