{"id":"W3113846595","doi":"10.1109/pesgm41954.2020.9281703","title":"Deep Reinforcement Learning for Direct Load Control in Distribution Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"News aggregator; Reinforcement learning; Markov decision process; Computer science; Control (management); Markov process; Artificial neural network; Mathematical optimization; Demand response; Markov chain; Operations research; Artificial intelligence; Engineering; Electricity; Machine learning","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":[0.0001119716,0.00009782703,0.0001261795,0.0000143787,0.00002512591,0.00002044395,0.00006561611,0.00003647268,0.00005461308],"category_scores_gemma":[0.00004769921,0.0001001088,0.00004022064,0.0001234578,0.000005025459,0.00006067282,0.00001948515,0.00008669084,0.00001349424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001651308,"about_ca_system_score_gemma":0.000003520581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001711317,"about_ca_topic_score_gemma":0.000033895,"domain_scores_codex":[0.9993821,0.00001005897,0.0001712301,0.0001179721,0.00009046988,0.0002281343],"domain_scores_gemma":[0.9998019,0.00004546132,0.00001380214,0.00006761158,0.0000163749,0.00005479364],"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":[0.00001969194,0.000002434295,0.0005571172,0.00002081589,0.00002749858,0.000001349234,0.00003359638,0.9929258,0.00003183655,0.0006359923,0.004187965,0.001555934],"study_design_scores_gemma":[0.0007757539,0.00003956826,0.0005850936,0.000006202893,0.00001000374,7.086553e-8,0.00002306607,0.9331178,0.0001018441,0.000003768047,0.06522806,0.0001087781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006813437,0.0001158073,0.9878511,0.0002403234,0.0001883676,0.0002493226,3.742844e-7,0.0003270971,0.0103462],"genre_scores_gemma":[0.9990868,0.00003478257,0.0001290764,0.0002573523,0.0001718512,0.0001041989,0.00006268627,0.00001721841,0.0001360071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9984055,"threshold_uncertainty_score":0.4082317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006725091412160987,"score_gpt":0.1828811759495285,"score_spread":0.1761560845373676,"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."}}