{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007616085,0.0009055281,0.0009799987,0.000555579,0.001095237,0.000322272,0.001976872,0.0008361319,0.0001420168],"category_scores_gemma":[0.009046149,0.0009969268,0.0002440113,0.001107523,0.0001590817,0.001662851,0.001024594,0.002764528,0.0002278472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001184718,"about_ca_system_score_gemma":0.0001065993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00035348,"about_ca_topic_score_gemma":0.0007279193,"domain_scores_codex":[0.9906481,0.0008425698,0.001795669,0.004314621,0.001293011,0.001106065],"domain_scores_gemma":[0.9927472,0.00040354,0.001034162,0.004861493,0.0005863112,0.0003672576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006628223,0.000527547,0.005609924,0.002921774,0.0004531608,0.0002070125,0.0006307872,0.2201247,0.008590429,0.1712305,0.00001720563,0.5890242],"study_design_scores_gemma":[0.009990582,0.006348495,0.1078888,0.00519819,0.0006580821,0.0002217089,0.002252697,0.3509599,0.1173117,0.123316,0.2605669,0.01528695],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8851706,0.0002781978,0.0008874748,0.00005460556,0.002545171,0.001958278,0.00001014716,0.0008518077,0.1082437],"genre_scores_gemma":[0.9775847,0.0002033589,0.0114465,0.0001497477,0.00006298332,0.0001219994,0.0002472016,0.0001131434,0.01007032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5737372,"threshold_uncertainty_score":0.9995362,"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."}}