{"id":"W4212900071","doi":"10.1177/14780771211069999","title":"The use of reinforced learning to support multidisciplinary design in the AEC industry: Assessing the utilization of Markov Decision Process","year":2022,"lang":"en","type":"article","venue":"International Journal of Architectural Computing","topic":"BIM and Construction Integration","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Multidisciplinary approach; Markov decision process; Process (computing); Engineering design process; Engineering; Risk analysis (engineering); Systems engineering; Decision support system; Management science; Architecture; Computer science; Engineering management; Artificial intelligence; Markov process; Business; Mechanical engineering","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":[0.001148855,0.00008161143,0.0001067202,0.0001971992,0.0002253706,0.00009519671,0.0005184635,0.00002929097,0.00001256931],"category_scores_gemma":[0.0003691679,0.00004562086,0.00006719452,0.0003210402,0.00004401514,0.0001642148,0.0001021305,0.0007606673,1.467924e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007604891,"about_ca_system_score_gemma":0.00006929016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001131718,"about_ca_topic_score_gemma":0.00000493899,"domain_scores_codex":[0.998385,0.0002368488,0.0006021377,0.00006152983,0.0006119644,0.0001025943],"domain_scores_gemma":[0.9981211,0.001154636,0.0003633415,0.00007602228,0.0002665204,0.000018324],"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":[0.00007345558,0.000004342973,0.002504384,0.000003209561,0.00002531201,0.000003412695,0.003318602,0.8179344,0.001009976,0.00008427078,0.00002976412,0.1750089],"study_design_scores_gemma":[0.0003528342,0.000194323,0.03012652,0.000170537,0.00001397069,0.0005907615,0.006253009,0.9592533,0.002218497,0.0003723832,0.0003681827,0.0000857315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8594229,0.00002620115,0.1395258,0.0003465754,0.0005101507,0.0001135194,0.000001381206,0.000008106015,0.00004543617],"genre_scores_gemma":[0.9966683,0.000003649602,0.00318668,0.00003114708,0.00008775164,0.00000284566,0.000002389083,0.000008320469,0.000008874744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1749232,"threshold_uncertainty_score":0.3304763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04876883625864213,"score_gpt":0.3259206915831386,"score_spread":0.2771518553244964,"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."}}