{"id":"W3214969471","doi":"","title":"Personal Comfort Estimation in Partial Observable Environment using Reinforcement Learning.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Preference; Forgetting; Computer science; Set (abstract data type); Home automation; Artificial intelligence; Thermal comfort; Bayesian probability; Machine learning; Human–computer interaction; Simulation; Mathematics; Statistics; Psychology","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":[0.0005435557,0.0005548748,0.0005407337,0.0002008488,0.000157505,0.0003375204,0.0005317171,0.00045234,0.001057434],"category_scores_gemma":[0.002596892,0.0002683592,0.0003174398,0.0001545911,0.0003899715,0.0007261293,0.0005601982,0.0006963305,0.0001588422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005501154,"about_ca_system_score_gemma":0.0005130502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00679806,"about_ca_topic_score_gemma":0.007087796,"domain_scores_codex":[0.9997571,0.00008789566,0.00001079198,0.00006011298,0.00004998648,0.00003410743],"domain_scores_gemma":[0.9991768,0.0005387369,0.00008454353,0.00004744824,0.0001062662,0.00004612958],"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":[0.00009763785,0.00006146044,0.001543352,0.0000322929,0.00003081748,0.00003332946,0.00003501112,0.9662541,0.001328087,0.001380125,0.0004259819,0.02877776],"study_design_scores_gemma":[0.000003077952,0.0000114853,0.0001252664,0.000001317858,0.000001727257,0.000003115571,0.000002297456,0.9988621,0.0001988806,0.0007416413,0.00004774631,0.000001299556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08699738,0.0002668211,0.9104298,0.0001776169,0.00003174197,0.0000347501,0.00006888556,0.0004700596,0.001522973],"genre_scores_gemma":[0.9577135,0.00005226729,0.04125394,0.00004974459,0.000008979154,0.00002969734,0.00007184889,0.00002073299,0.0007992606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00679806,"threshold_uncertainty_score":0.01351696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05272458894793218,"score_gpt":0.1643046880286961,"score_spread":0.111580099080764,"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."}}