{"id":"W4242162370","doi":"10.26868/25222708.2019.211427","title":"A Simplified Building Controls Environment with a Reinforcement Learning Application","year":2020,"lang":"en","type":"article","venue":"Building Simulation Conference proceedings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Concordia University","funders":"McGill University","keywords":"Reinforcement learning; HVAC; Computer science; Matching (statistics); Control (management); Reinforcement; Energy consumption; Building automation; Air conditioning; Control engineering; Simulation; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001233946,0.0002772516,0.0002466921,0.00009201061,0.0001945083,0.0001674683,0.0001875154,0.0001189361,0.00005847493],"category_scores_gemma":[0.00004429978,0.0002780588,0.00004455268,0.0002791034,0.00003479095,0.0004508567,0.00004492695,0.000273839,0.000008310169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001000344,"about_ca_system_score_gemma":0.00002096756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004300994,"about_ca_topic_score_gemma":2.381709e-7,"domain_scores_codex":[0.9986114,0.000007014745,0.0003515417,0.000381111,0.0003256499,0.0003232788],"domain_scores_gemma":[0.9994379,0.00005115062,0.0001431943,0.00009209728,0.0001154167,0.0001602541],"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":[0.00005744449,0.00000741275,0.001222576,0.00006234086,0.00003804687,4.566754e-7,0.0005030175,0.9628822,0.01938292,0.01217294,0.00001908972,0.003651582],"study_design_scores_gemma":[0.0006873127,0.000116246,0.0001258768,0.00005580255,0.00003614005,0.000001808771,0.0001029275,0.9878833,0.004568224,0.0003056997,0.005770346,0.0003463542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1990401,0.00002677952,0.798804,0.0002038426,0.00002055718,0.000360981,6.724349e-7,0.0007274266,0.0008156752],"genre_scores_gemma":[0.988624,0.0000274901,0.0108099,0.0001761739,0.0001242875,0.0001299918,0.00001892214,0.00005754281,0.00003171022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7895839,"threshold_uncertainty_score":0.9999672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01379501994551633,"score_gpt":0.2115118368166087,"score_spread":0.1977168168710924,"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."}}