{"id":"W4399686980","doi":"10.1007/s10664-024-10500-5","title":"Common challenges of deep reinforcement learning applications development: an empirical study","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec; Canadian Institute for Advanced Research","keywords":"Computer science; Taxonomy (biology); Leverage (statistics); Popularity; Reinforcement learning; Artificial intelligence; Data science; Software engineering","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":[0.0006953875,0.0003003182,0.0003477062,0.0004366496,0.0001231063,0.0001670125,0.001022563,0.0001203902,0.00002095144],"category_scores_gemma":[0.0004939103,0.0002956362,0.00008712632,0.001054331,0.00002598405,0.0004731008,0.0005112478,0.0006538911,0.00007049194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002136749,"about_ca_system_score_gemma":0.0001132977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006231698,"about_ca_topic_score_gemma":0.00000429308,"domain_scores_codex":[0.9974092,0.00006937222,0.0005384495,0.0006826479,0.000757054,0.0005432225],"domain_scores_gemma":[0.9975057,0.001379043,0.00004061229,0.0006885441,0.00009693089,0.0002891804],"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":[0.000009076185,0.0006328684,0.2484292,0.0008604064,0.0002985133,0.0001408035,0.01819609,0.5643942,0.0001076644,0.001012003,0.0001065137,0.1658126],"study_design_scores_gemma":[0.0005427838,0.0009020171,0.3667878,0.0002387159,0.00003202899,0.00004922521,0.0003048101,0.5819047,0.00102651,0.0001338379,0.04693265,0.001144882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1120027,0.001929107,0.8830235,0.0001208122,0.0001973222,0.0004470876,3.307329e-7,0.002248028,0.00003109991],"genre_scores_gemma":[0.9631806,0.00002390165,0.03624717,0.00001611213,0.0001164834,0.0003100881,0.000007683204,0.00005620438,0.00004173433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8511779,"threshold_uncertainty_score":0.9999496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03930345304508256,"score_gpt":0.3277676583422513,"score_spread":0.2884642052971688,"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."}}