{"id":"W4387723770","doi":"10.48550/arxiv.2310.09575","title":"Common Challenges of Deep Reinforcement Learning Applications Development: An Empirical Study","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec; Canadian Institute for Advanced Research","keywords":"Computer science; Reinforcement learning; Taxonomy (biology); Popularity; Leverage (statistics); Artificial intelligence; Data science; Software engineering; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009320072,0.0004153136,0.0004156025,0.002653415,0.001236489,0.001809352,0.0009167106,0.001064434,0.0009932938],"category_scores_gemma":[0.08354793,0.0004670413,0.0003571064,0.002656255,0.001204679,0.003589534,0.002015277,0.001606229,0.0004795673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001264988,"about_ca_system_score_gemma":0.001710789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003687215,"about_ca_topic_score_gemma":0.006585799,"domain_scores_codex":[0.9903866,0.003415463,0.001166631,0.001155508,0.003237517,0.0006383811],"domain_scores_gemma":[0.8217056,0.1204749,0.02912013,0.005938452,0.01915001,0.003611009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003776267,0.001358609,0.8633225,0.0007967096,0.00007199789,0.001071016,0.02899858,0.00133368,0.00270143,0.0009391633,0.003493496,0.09553514],"study_design_scores_gemma":[0.0000552371,0.001267264,0.9013097,0.0005283753,0.00007943036,0.001922345,0.05156536,0.02413174,0.003470384,0.001280226,0.01426033,0.0001295978],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973411,0.0001998508,0.001082468,0.0002281917,0.000006451238,0.00008125415,0.0001422776,0.00003803231,0.000880416],"genre_scores_gemma":[0.9963065,0.0002711591,0.002267861,0.0001208673,0.00001287136,0.0001108031,0.0003513037,0.0000345366,0.0005241563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009320072,"threshold_uncertainty_score":0.04928982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1551412959779371,"score_gpt":0.2693460052794603,"score_spread":0.1142047093015232,"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."}}