{"id":"W3210905397","doi":"10.1016/j.epsr.2022.108375","title":"Batch reinforcement learning for network-safe demand response in unknown electric grids","year":2022,"lang":"en","type":"article","venue":"Electric Power Systems Research","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency - Energy; Institut de Valorisation des Données; National Science Foundation","keywords":"Demand response; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Engineering; Electricity; Electrical engineering; Structural engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01182708,0.000292632,0.0004260776,0.00171041,0.0006619871,0.0001427045,0.00069433,0.0001076904,0.0001335251],"category_scores_gemma":[0.0004222738,0.0003302415,0.0001050473,0.005099977,0.00001807502,0.0001327035,0.0003098418,0.001451311,0.00005278421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002461695,"about_ca_system_score_gemma":0.0002100644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001843118,"about_ca_topic_score_gemma":0.00001306535,"domain_scores_codex":[0.99366,0.001573915,0.0007127324,0.0005443706,0.001454782,0.002054148],"domain_scores_gemma":[0.998042,0.00102443,0.0000652407,0.0005438662,0.0001520477,0.0001724345],"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":[0.0007011288,0.00003394813,0.0003089018,0.0001003497,0.00009429935,0.00005214462,0.0002035495,0.947875,0.00236364,0.001098114,0.04677238,0.0003965365],"study_design_scores_gemma":[0.0008217804,0.00100956,0.001037557,0.00002880462,0.000006488746,0.00001728316,0.0001127997,0.6468301,0.0002738431,0.0000347493,0.3495376,0.0002893583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7456158,0.03067751,0.1658859,0.0006372921,0.006587102,0.008833735,0.000005312759,0.001435977,0.04032141],"genre_scores_gemma":[0.98491,0.0002344062,0.00003105221,0.00002007136,0.0002654014,0.003053254,0.00002084259,0.0001182682,0.01134678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3027652,"threshold_uncertainty_score":0.9999149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02116056373868598,"score_gpt":0.2769639480123283,"score_spread":0.2558033842736423,"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."}}