{"id":"W4408343532","doi":"10.2139/ssrn.5101465","title":"Towards Sustainable Energy Use: Reinforcement Learning for Demand Response in Commercial Buildings","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; HEC Montréal","funders":"","keywords":"Reinforcement; Demand response; Reinforcement learning; Sustainable energy; Energy (signal processing); Energy demand; Architectural engineering; Environmental economics; Business; Natural resource economics; Computer science; Economics; Engineering; Artificial intelligence; Renewable energy; Electricity; Structural 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001356833,0.0004047835,0.0006096044,0.0001757251,0.0002028592,0.0007785469,0.0006135789,0.0008931222,0.002612959],"category_scores_gemma":[0.005505696,0.0002414977,0.0003002411,0.0002820948,0.0006221466,0.001097812,0.0008389797,0.001507045,0.0001861077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007000773,"about_ca_system_score_gemma":0.0007764931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006123097,"about_ca_topic_score_gemma":0.004148314,"domain_scores_codex":[0.9996716,0.0001910201,0.0000104386,0.00004329785,0.00004720438,0.0000364045],"domain_scores_gemma":[0.9978952,0.001723366,0.00008359787,0.0000679482,0.0001607953,0.00006896882],"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":[0.00007752942,0.00007885938,0.0007181229,0.00006084572,0.00002765533,0.00002387365,0.00005122374,0.9539496,0.0005460113,0.0124452,0.0008750563,0.03114609],"study_design_scores_gemma":[0.000004746979,0.000008711743,0.00006078133,0.000002697221,0.000001737522,0.000001910644,0.000006398344,0.9938728,0.00009120461,0.005841166,0.0001066938,0.000001230568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.132301,0.0005963131,0.8579878,0.001633399,0.00008731527,0.00005638864,0.00005677803,0.0002214374,0.007059576],"genre_scores_gemma":[0.972041,0.0001920098,0.02524396,0.00007072186,0.00003440275,0.00003442149,0.00003653617,0.00003498423,0.002311951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006123097,"threshold_uncertainty_score":0.0121749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007915999871737868,"score_gpt":0.2343478632175671,"score_spread":0.2264318633458292,"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."}}