{"id":"W4399771495","doi":"10.32920/26052415.v1","title":"Development of a Model-free Reinforcement Learning for a Heat Recovery Chiller System Optimization","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Polytechnique Montréal; Sciencetech (Canada)","funders":"Connaught Fund","keywords":"Reinforcement learning; Chiller; Chiller boiler system; Reinforcement; Computer science; Water chiller; Environmental science; Engineering; Artificial intelligence; Mechanical engineering; Thermodynamics; Heat exchanger; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.001193706,0.0007126324,0.0007695071,0.0002492492,0.0003193202,0.0006521185,0.001179405,0.001134947,0.00386311],"category_scores_gemma":[0.002861697,0.0004805189,0.0006674452,0.000164069,0.0006524872,0.0005702453,0.001038998,0.002109144,0.0005247609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008674717,"about_ca_system_score_gemma":0.001867159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008952327,"about_ca_topic_score_gemma":0.006128375,"domain_scores_codex":[0.9996321,0.0001028037,0.00001800725,0.0000772903,0.0001177641,0.00005208664],"domain_scores_gemma":[0.9989296,0.0006517653,0.00007197118,0.00006534353,0.0002260972,0.0000552395],"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":[0.0000348277,0.0000479023,0.0002987764,0.00003811888,0.00001687402,0.00003835741,0.00002651068,0.9760447,0.001453502,0.003519072,0.0004115917,0.01806979],"study_design_scores_gemma":[0.000005114314,0.00001537116,0.00002275893,0.000002172782,0.000001668823,0.000002328224,0.000001443341,0.9992533,0.0002130878,0.0003097046,0.0001716376,0.000001238578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01757416,0.0001160359,0.9753946,0.0002758126,0.00005256907,0.0001188269,0.00004652652,0.0007788654,0.005642644],"genre_scores_gemma":[0.6975676,0.00009931088,0.2957878,0.0002182899,0.00003860436,0.0003552156,0.0001131965,0.0001387631,0.005681125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008952327,"threshold_uncertainty_score":0.01780045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01523720484585806,"score_gpt":0.2084965542871615,"score_spread":0.1932593494413035,"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."}}