{"id":"W3131309288","doi":"10.1109/twc.2020.3029143","title":"Deep Reinforcement Learning for Delay-Oriented IoT Task Scheduling in SAGIN","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"UAV Applications and Optimization","field":"Engineering","cited_by":319,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Markov decision process; Scheduling (production processes); Probabilistic logic; Energy consumption; Distributed computing; Base station; Real-time computing; Online algorithm; Markov process; Markov chain; Mathematical optimization; Artificial intelligence; Computer network; Machine learning; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001007889,0.0008131093,0.000983026,0.0002665409,0.0003336625,0.0006467751,0.0008846485,0.0009516022,0.001553089],"category_scores_gemma":[0.002981046,0.0003933217,0.0003335471,0.0002659806,0.0008056977,0.0007799805,0.0008682114,0.001295919,0.0001467315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00113805,"about_ca_system_score_gemma":0.001628824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008044941,"about_ca_topic_score_gemma":0.006934092,"domain_scores_codex":[0.999649,0.0001053138,0.00001464941,0.0000828787,0.00005580282,0.00009237996],"domain_scores_gemma":[0.9987652,0.0008166487,0.0001360549,0.00004079059,0.0001467842,0.00009444779],"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":[0.0000558546,0.00004174827,0.000639889,0.00002383697,0.00001505358,0.00003160556,0.00001950786,0.9879061,0.0003914399,0.001789027,0.0003102292,0.008775747],"study_design_scores_gemma":[0.000003916343,0.00001083179,0.00004488352,0.000001606205,0.000001784324,0.000002311127,0.000002678731,0.9989329,0.00006475683,0.0008804153,0.00005280527,9.757199e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1374289,0.000715615,0.8568121,0.000728758,0.0000904118,0.00006944791,0.00008376522,0.0004329205,0.003638101],"genre_scores_gemma":[0.9717525,0.0001249453,0.0262553,0.0001642547,0.00002280273,0.00005916119,0.00006969588,0.00003396084,0.001517436],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008044941,"threshold_uncertainty_score":0.01599622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02033895183417698,"score_gpt":0.2452898599437185,"score_spread":0.2249509081095415,"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."}}