{"id":"W4389074848","doi":"10.1007/s10994-023-06460-4","title":"Multi-agent reinforcement learning for fast-timescale demand response of residential loads","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Group for Research in Decision Analysis; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung; Institut de Valorisation des Données; Microsoft Research","keywords":"Reinforcement learning; Computer science; Demand response; Renewable energy; Distributed computing; Power (physics); Artificial intelligence; Engineering; Electrical engineering; Electricity","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":[0.001213377,0.0002322039,0.0002834575,0.0003886252,0.00019165,0.00004094785,0.0002054287,0.00007877451,0.0001372593],"category_scores_gemma":[0.0003869203,0.0002523694,0.0001433756,0.0004117501,0.0000296968,0.0001010821,0.0001878374,0.0002848018,0.0001058407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009503617,"about_ca_system_score_gemma":0.00001312161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005825207,"about_ca_topic_score_gemma":0.00002089833,"domain_scores_codex":[0.998373,0.0001505809,0.0004409916,0.0002665637,0.0002989005,0.0004699039],"domain_scores_gemma":[0.9992807,0.0002544712,0.00009385261,0.0002405628,0.00004479216,0.00008561288],"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":[0.0002016124,0.00001023163,0.004157602,0.0001583504,0.0001101081,0.00001184463,0.0006104648,0.9669455,0.02485532,0.00002487602,0.001704221,0.001209868],"study_design_scores_gemma":[0.001184943,0.0001628924,0.01312502,0.00005635919,0.00004057215,0.000001661291,0.0001682009,0.9344265,0.007762736,0.000005450216,0.042824,0.000241636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6075171,0.0002676276,0.3884405,0.0001571841,0.0008065208,0.000498897,0.00000362073,0.001426048,0.0008824805],"genre_scores_gemma":[0.9829456,0.00007661959,0.002129286,0.00001608271,0.000133795,0.0000937915,0.00009296183,0.00009784589,0.01441402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3863112,"threshold_uncertainty_score":0.9999928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01256083026442792,"score_gpt":0.2416896789584488,"score_spread":0.2291288486940209,"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."}}