{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001607278,0.0001377375,0.0001960722,0.000230585,0.00006716236,0.00001990808,0.00009654429,0.00009558697,0.000043788],"category_scores_gemma":[0.000008398119,0.0001702493,0.00005613168,0.0004984022,0.00002837036,0.0001408147,7.534188e-7,0.0003306998,2.283087e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001220815,"about_ca_system_score_gemma":0.00008865503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004078938,"about_ca_topic_score_gemma":0.00008881018,"domain_scores_codex":[0.9989818,0.00007153954,0.0003818432,0.0002038422,0.0001915896,0.0001693559],"domain_scores_gemma":[0.999599,0.0001042554,0.00004964746,0.0001139358,0.00009805107,0.000035126],"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":[0.00002599519,0.0000637845,0.00002737576,0.00002567674,0.00001664226,0.000004356692,0.0004317665,0.9842315,0.009164927,0.0007257794,3.808675e-7,0.005281777],"study_design_scores_gemma":[0.000288196,0.00003552427,0.00003464127,0.0001171105,0.000006890389,0.000001609463,0.00009330492,0.9014481,0.09732,0.000504414,0.000008683405,0.0001415318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.257848,0.00002878876,0.7417167,0.00003292931,0.0002303876,0.00006050998,0.000002298379,0.00005072115,0.0000296575],"genre_scores_gemma":[0.9685336,0.00002388362,0.03129267,0.00006699929,0.0000227831,0.00001643449,0.00001153918,0.00001732251,0.00001481704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7106856,"threshold_uncertainty_score":0.6942567,"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."}}