{"id":"W4386185028","doi":"10.48550/arxiv.2308.12438","title":"Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Open Source Software Innovations","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","keywords":"Software deployment; Reinforcement learning; Computer science; Enthusiasm; Artificial intelligence; Autonomy; Data science; Software engineering; Political science; Psychology","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":[0.0116014,0.0008058241,0.0006370221,0.001855127,0.001124732,0.002934638,0.001565716,0.001813523,0.001290746],"category_scores_gemma":[0.05175142,0.0006927975,0.0005185108,0.002044935,0.001821054,0.006283247,0.002772872,0.00278001,0.0005462153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002212296,"about_ca_system_score_gemma":0.002754231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005034243,"about_ca_topic_score_gemma":0.004850551,"domain_scores_codex":[0.9867181,0.005059693,0.001460701,0.00148074,0.004324103,0.000956779],"domain_scores_gemma":[0.9415559,0.0383334,0.006138061,0.003914635,0.008446944,0.001611101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004425836,0.0004804468,0.09994248,0.003552194,0.0001177333,0.002157531,0.01364968,0.03152151,0.01679911,0.0345916,0.02165762,0.7750874],"study_design_scores_gemma":[0.0001164736,0.001587203,0.08814382,0.003408314,0.0001454921,0.005796372,0.03698493,0.4905114,0.03096412,0.06315617,0.2786649,0.0005208139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5370992,0.01389622,0.3813507,0.03312953,0.0006601592,0.001219539,0.0009184662,0.003911722,0.02781438],"genre_scores_gemma":[0.8734401,0.004680934,0.1137331,0.002521367,0.000235476,0.000454974,0.0007520348,0.0004150335,0.003766917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0116014,"threshold_uncertainty_score":0.06135482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1837989261232988,"score_gpt":0.2076928440857742,"score_spread":0.02389391796247539,"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."}}