{"id":"W3207692912","doi":"10.1016/j.apenergy.2022.120500","title":"Multi-agent hierarchical reinforcement learning for energy management","year":2022,"lang":"en","type":"article","venue":"Applied Energy","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":97,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Group for Research in Decision Analysis","funders":"Trottier Institute for Sustainability in Engineering and Design","keywords":"Reinforcement learning; Computer science; Scheduling (production processes); Novelty; Energy management; Control engineering; Efficient energy use; Distributed computing; Energy (signal processing); Artificial intelligence; 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":[0.0001921317,0.0003123634,0.0002480919,0.0002619631,0.0003973033,0.00003854888,0.0004187794,0.00004873326,0.0003186865],"category_scores_gemma":[0.0000022812,0.0003701377,0.000129399,0.0003048204,0.00002700849,0.00004071219,0.0005254107,0.000185022,0.00001276576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000399582,"about_ca_system_score_gemma":0.00000882328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004629889,"about_ca_topic_score_gemma":0.00001546884,"domain_scores_codex":[0.9980832,0.00002950281,0.0003850509,0.0004338846,0.0004334604,0.0006349161],"domain_scores_gemma":[0.9993377,0.00004659003,0.00005127517,0.0004194307,0.00001284991,0.0001321449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002927731,0.00004962995,0.0000032295,0.00003404831,0.0001995473,0.00001065252,0.00005290978,0.7703685,0.0006329614,0.2039945,0.009304734,0.01531999],"study_design_scores_gemma":[0.0008419189,0.00005520502,0.00003163759,0.000002561407,0.00003066158,0.000001568961,0.0001061674,0.3688627,0.001158855,0.0003300496,0.6282829,0.0002957623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009450855,0.0001624637,0.9319738,0.00007351704,0.001110984,0.0002447176,0.000003390295,0.0008864639,0.06459959],"genre_scores_gemma":[0.9769133,0.0001971755,0.007329333,0.0005964167,0.0002321377,0.00440876,0.0002878724,0.0001384539,0.009896582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9759682,"threshold_uncertainty_score":0.9998751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01014517915541733,"score_gpt":0.1966193987083418,"score_spread":0.1864742195529245,"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."}}