{"id":"W7042992782","doi":"","title":"Reproducibility and reusability in deep reinforcement learning","year":2018,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reproducibility; Reinforcement learning; Reusability; Reinforcement; Reliability (semiconductor)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02306304,0.001418957,0.00167397,0.0009700421,0.0009551989,0.002809233,0.003735819,0.002143216,0.002506767],"category_scores_gemma":[0.1193959,0.001098722,0.001626052,0.0007708921,0.006263725,0.00562403,0.006198639,0.004896394,0.000535745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002170387,"about_ca_system_score_gemma":0.001942843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002023483,"about_ca_topic_score_gemma":0.001410944,"domain_scores_codex":[0.9814802,0.009276077,0.001323345,0.00381533,0.003366407,0.0007387926],"domain_scores_gemma":[0.8812489,0.08211005,0.00670551,0.02482745,0.003742258,0.001365808],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005537378,0.0002853024,0.004589696,0.0003670986,0.0002037207,0.0002709039,0.0005818121,0.8332092,0.006038129,0.08136944,0.0008012469,0.0717297],"study_design_scores_gemma":[0.0000670194,0.0002711608,0.0006171147,0.0000453687,0.00003117559,0.00005971912,0.00004802169,0.8999271,0.005065293,0.09291495,0.0009147742,0.0000382388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08327886,0.0003660298,0.9115003,0.0005273389,0.00005820331,0.0001646673,0.00009968381,0.001331881,0.002672956],"genre_scores_gemma":[0.8754098,0.000180856,0.1213282,0.0002212062,0.00005143442,0.0004879968,0.0002193398,0.000513823,0.00158721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9769369,"threshold_uncertainty_score":0.1219705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01847197167670655,"score_gpt":0.2572029638222421,"score_spread":0.2387309921455356,"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."}}