{"id":"W3159962257","doi":"10.1109/tetci.2021.3066999","title":"An Enhanced Adaptivity of Reinforcement Learning-Based Temperature Control in Buildings Using Generalized Training","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Controller (irrigation); Computer science; Convergence (economics); Generalization; Control theory (sociology); Control (management); Reinforcement; State (computer science); Reduction (mathematics); Temperature control; Adaptive control; Control engineering; Artificial intelligence; Engineering; Algorithm; 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":[0.0004655746,0.0003869885,0.0004156065,0.0001327357,0.000127638,0.0002845315,0.0006228372,0.0003150459,0.0007700517],"category_scores_gemma":[0.001197494,0.0001497887,0.0002871652,0.0001126499,0.0004385971,0.0003460168,0.0005270306,0.0004833047,0.0001161902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002051815,"about_ca_system_score_gemma":0.0003063015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003439047,"about_ca_topic_score_gemma":0.002007954,"domain_scores_codex":[0.9998022,0.00006804611,0.000008462884,0.00004654134,0.00004561821,0.00002914238],"domain_scores_gemma":[0.9996911,0.0001461647,0.00004128294,0.00004450806,0.00006008666,0.00001687983],"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":[0.00008242435,0.00005921,0.0005396201,0.00005543211,0.00003069232,0.00004912933,0.00006475789,0.9225573,0.009966346,0.003028983,0.0003688132,0.06319729],"study_design_scores_gemma":[0.000004773316,0.00003889573,0.0001171283,0.000002456191,0.000003292692,0.000007866994,0.000001717275,0.9985104,0.0007292564,0.000375229,0.000206722,0.000002354954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06655482,0.0002173134,0.9294662,0.00008827914,0.00005200424,0.0000347538,0.00001074819,0.0005181901,0.00305774],"genre_scores_gemma":[0.9727033,0.00004969787,0.02612366,0.00003915083,0.00001905637,0.00002798325,0.00001318579,0.00002292961,0.001001037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003439047,"threshold_uncertainty_score":0.006838024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530769114142567,"score_gpt":0.2783273893375252,"score_spread":0.2530196981960995,"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."}}