{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009334612,0.0001641142,0.0001718545,0.0001540284,0.0003478829,0.0000355035,0.000383604,0.00009405268,0.00002901801],"category_scores_gemma":[0.000007436176,0.0002010563,0.0000806079,0.000654758,0.0000505971,0.0001128376,0.000004410645,0.00044469,0.00003427441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273643,"about_ca_system_score_gemma":0.00002436965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002934911,"about_ca_topic_score_gemma":0.0001651786,"domain_scores_codex":[0.9990439,0.00004075842,0.0003925101,0.0001884483,0.0001096639,0.000224697],"domain_scores_gemma":[0.9990071,0.0001635468,0.00004991576,0.0005968716,0.00008210594,0.0001004786],"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":[0.00001395784,0.00006155227,0.0000169677,0.00002743823,0.00002986554,1.333478e-7,0.0009126028,0.9852787,0.00195914,0.0009408724,0.00001406072,0.01074467],"study_design_scores_gemma":[0.0005715434,0.00004597549,0.00002357371,0.00003392193,0.0000277515,8.167219e-7,0.000290448,0.9936381,0.002447676,0.00002037944,0.002705998,0.0001938295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01154297,0.0001320692,0.9858307,0.0009591853,0.00007125936,0.0005933369,0.000007505824,0.0003825286,0.0004804221],"genre_scores_gemma":[0.9664888,0.0006203417,0.03180496,0.0001321099,0.00001813913,0.0007739923,0.00007668943,0.00005059412,0.00003441963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9549458,"threshold_uncertainty_score":0.8198839,"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."}}