{"id":"W4311169764","doi":"10.1088/1755-1315/1101/9/092027","title":"Development of the Reward Function to support Model-Free Reinforcement Learning for a Heat Recovery Chiller System Optimization","year":2022,"lang":"en","type":"article","venue":"IOP Conference Series Earth and Environmental Science","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fuseforward (Canada); Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Chiller; Reinforcement; Computer science; Function (biology); Generalization; Bellman equation; Operator (biology); Artificial intelligence; Engineering; Mathematical optimization; Mathematics","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":[0.001985407,0.0006865662,0.000728739,0.0003291216,0.0003173015,0.0006751035,0.001043712,0.0009622216,0.002771207],"category_scores_gemma":[0.003941507,0.0003915897,0.0004552239,0.0001498121,0.0005334967,0.0005602124,0.0007066237,0.001642536,0.0005204275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008164568,"about_ca_system_score_gemma":0.00186735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005742855,"about_ca_topic_score_gemma":0.002895933,"domain_scores_codex":[0.9995983,0.0001637529,0.00002388627,0.00004899225,0.000113729,0.00005146471],"domain_scores_gemma":[0.9986889,0.0007599112,0.00007661097,0.00006753142,0.0003517715,0.0000552174],"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":[0.00003399294,0.00005613924,0.0003532787,0.00002931431,0.00001202975,0.00004734906,0.0000260239,0.9670492,0.002782357,0.005256443,0.0003277733,0.02402618],"study_design_scores_gemma":[0.000004132726,0.0000102122,0.00001936575,0.000001518183,8.710173e-7,0.000002191137,8.668904e-7,0.999099,0.0005097917,0.0002330648,0.0001177478,0.000001233996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0157541,0.00003104403,0.9815474,0.0001303086,0.00002379162,0.00008222897,0.00001895564,0.0007007837,0.001711366],"genre_scores_gemma":[0.6193704,0.00005065055,0.3776492,0.00009080836,0.0000198995,0.0003140389,0.00005628073,0.0001761068,0.002272558],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005742855,"threshold_uncertainty_score":0.01141882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00958776966291503,"score_gpt":0.1646415380832033,"score_spread":0.1550537684202883,"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."}}