{"id":"W4385408633","doi":"10.1007/s12273-023-1056-7","title":"A reinforcement learning approach for thermostat setpoint preference learning","year":2023,"lang":"en","type":"article","venue":"Building Simulation","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brain Canada Foundation; Concordia University; Carleton University","funders":"","keywords":"Thermostat; Setpoint; Reinforcement learning; Reinforcement; Computer science; Thermal comfort; Python (programming language); Efficient energy use; Simulation; Energy (signal processing); Artificial intelligence; Engineering; Mathematics; Mechanical 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":[0.00143748,0.0005933337,0.001310155,0.0004174789,0.0004249409,0.0006305246,0.001975387,0.001208829,0.005793421],"category_scores_gemma":[0.004040023,0.0005230358,0.0006050691,0.0005144893,0.0007752558,0.0009972954,0.001242371,0.001926975,0.0004875171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000861336,"about_ca_system_score_gemma":0.001128324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008228825,"about_ca_topic_score_gemma":0.007108975,"domain_scores_codex":[0.9994718,0.0002180514,0.00002439119,0.00008765097,0.0001361834,0.00006181571],"domain_scores_gemma":[0.9983975,0.001054521,0.0000819116,0.00008835513,0.0002837897,0.00009398738],"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":[0.0000706974,0.0001008658,0.0003026954,0.00003137427,0.00003024047,0.00002751056,0.00002946053,0.9390742,0.0006898858,0.01069771,0.0006145022,0.04833083],"study_design_scores_gemma":[0.000007942004,0.00001326114,0.00001880219,0.000001471993,0.00000212189,0.000002711395,0.000001094051,0.9981083,0.00006839241,0.001694992,0.00007903422,0.000001878433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01010624,0.00009719608,0.9872991,0.0001172391,0.00003646244,0.00004381388,0.00002137376,0.0001570414,0.002121367],"genre_scores_gemma":[0.7728549,0.0001626398,0.2207053,0.0002056379,0.00009388627,0.0002487189,0.00008217508,0.00008777291,0.005558951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008228825,"threshold_uncertainty_score":0.01938093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03487764710691581,"score_gpt":0.2534986841133228,"score_spread":0.2186210370064069,"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."}}