{"id":"W3173438469","doi":"10.1109/access.2022.3156581","title":"Building Energy Management With Reinforcement Learning and Model Predictive Control: A Survey","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Model predictive control; Reinforcement learning; Computer science; Energy management; Building automation; Building management system; Efficient energy use; Renewable energy; Automation; Control (management); Energy (signal processing); Artificial intelligence; Engineering","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":[0.0003124331,0.000191346,0.0001782831,0.0001809926,0.0002192932,0.00009766461,0.0002927986,0.0000197384,0.00003294773],"category_scores_gemma":[0.000003346595,0.0001958786,0.00002242603,0.0002700159,0.00002251486,0.0002447062,0.0002696948,0.0001695951,6.75298e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001808045,"about_ca_system_score_gemma":0.000007676937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001704147,"about_ca_topic_score_gemma":0.00005087712,"domain_scores_codex":[0.9987952,0.00006507606,0.0001860935,0.0002747378,0.0003636027,0.0003152584],"domain_scores_gemma":[0.9996231,0.00004698833,0.00004689303,0.000188591,0.00002464322,0.0000697984],"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":[0.00008654447,0.00001089307,0.002752044,0.00003330383,0.0002763416,0.00002250714,0.00004788926,0.9930151,0.0000435993,0.001674519,0.001094606,0.0009426546],"study_design_scores_gemma":[0.0009787765,0.00008514194,0.003298599,0.00001317293,0.00005077847,0.0000032434,0.00004035598,0.9900542,0.0001940491,0.00009748441,0.004944132,0.0002400113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06709801,0.0001159709,0.9241084,0.00001888446,0.0003116638,0.0002049997,0.000007878138,0.000340149,0.007794002],"genre_scores_gemma":[0.9981585,0.0001029011,0.000506187,0.0001248533,0.00004359931,0.00042453,0.00001637694,0.00005445979,0.0005685749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9310605,"threshold_uncertainty_score":0.7987695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01109218519743361,"score_gpt":0.2253678702973813,"score_spread":0.2142756850999477,"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."}}