{"id":"W4320039231","doi":"10.1016/j.enbuild.2023.112878","title":"Mitigating an adoption barrier of reinforcement learning-based control strategies in buildings","year":2023,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Machine Intelligence Institute","keywords":"Reinforcement learning; Control (management); Set (abstract data type); Computer science; Population; Cluster analysis; Training (meteorology); Engineering; Architectural engineering; Machine learning; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002215787,0.0004470661,0.0006528103,0.00019217,0.000327792,0.0009100036,0.001006996,0.000826458,0.001495558],"category_scores_gemma":[0.01061371,0.000257508,0.0002325837,0.0001665467,0.0006060081,0.001205749,0.001059078,0.001484492,0.0001667582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005030502,"about_ca_system_score_gemma":0.0008560446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002678488,"about_ca_topic_score_gemma":0.001896166,"domain_scores_codex":[0.99879,0.0005770288,0.00005011924,0.0001356313,0.0002570356,0.0001902082],"domain_scores_gemma":[0.9930996,0.004695711,0.0007443794,0.0004019783,0.0008473316,0.0002110167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006329362,0.0006185013,0.004791767,0.0002610997,0.00008942791,0.0002057726,0.0003751271,0.830003,0.01897433,0.03911491,0.001216331,0.1037169],"study_design_scores_gemma":[0.00001806043,0.0002220671,0.0006451883,0.00001680565,0.00001200186,0.0000300137,0.00004473782,0.9930927,0.002167143,0.003346513,0.0003978648,0.000006935306],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3784506,0.0006718085,0.611198,0.0006495095,0.00008348652,0.0000786811,0.00001744333,0.0003585706,0.008491877],"genre_scores_gemma":[0.9948224,0.00003374334,0.00462493,0.00003413113,0.000005747469,0.00001069903,0.000003013279,0.00001031621,0.0004550866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002678488,"threshold_uncertainty_score":0.01171833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005628482034530541,"score_gpt":0.2013507305439212,"score_spread":0.1957222485093907,"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."}}