{"id":"W3047363982","doi":"10.1109/lwc.2020.3036094","title":"Learning Power Control From a Fixed Batch of Data","year":2020,"lang":"en","type":"preprint","venue":"IEEE Wireless Communications Letters","topic":"Smart Grid Security and Resilience","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Exploit; Reinforcement learning; Computer science; Control (management); Power (physics); Power control; Rest (music); Data transmission; Transmission (telecommunications); Artificial intelligence; Machine learning; Computer network; Computer security; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001841129,0.000278255,0.0005143306,0.0000931712,0.0001263625,0.00006317699,0.005085681,0.0002299698,0.00003305126],"category_scores_gemma":[0.00005193163,0.0003160409,0.0001147676,0.000174876,0.0002725832,0.000157655,0.001547959,0.001842303,0.00004342012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005274545,"about_ca_system_score_gemma":0.00005253758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000358574,"about_ca_topic_score_gemma":0.00008729366,"domain_scores_codex":[0.9983717,0.0002500158,0.0005125036,0.0003911279,0.0002499475,0.0002247062],"domain_scores_gemma":[0.994273,0.0005828195,0.0001784223,0.004824454,0.00005189671,0.0000894302],"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":[0.00006623497,0.000244623,0.003916884,0.0007147682,0.001907744,0.00002655243,0.01578282,0.5622822,0.3530258,0.0002393806,0.05545558,0.00633738],"study_design_scores_gemma":[0.000729589,0.00001863545,0.002322712,0.0005900508,0.0001861454,0.000002122298,0.000452591,0.9759923,0.002274407,0.00009489394,0.01661104,0.0007255395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8908908,0.003078416,0.08322999,0.01670597,0.001706111,0.0007450471,0.001870762,0.0008688122,0.0009040975],"genre_scores_gemma":[0.9930654,0.001110016,0.004112325,0.0004880506,0.000121883,0.00003333505,0.001007209,0.0000572966,0.000004526023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4137101,"threshold_uncertainty_score":0.9999292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04025398243726231,"score_gpt":0.2652640322137783,"score_spread":0.225010049776516,"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."}}