{"id":"W3034607397","doi":"","title":"An Optimistic Perspective on Offline Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Perspective (graphical); Artificial intelligence; Reinforcement; Machine learning; Psychology; Social psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003573012,0.0003404088,0.0002611411,0.0002165696,0.0003052919,0.0005476592,0.001700358,0.00008654805,0.0008736206],"category_scores_gemma":[0.001299779,0.0003351975,0.0001033555,0.0002624735,0.00005704588,0.0005289417,0.0002948053,0.00145189,0.000592829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002519226,"about_ca_system_score_gemma":0.0001022186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006817735,"about_ca_topic_score_gemma":0.00000241486,"domain_scores_codex":[0.9970936,0.0002444345,0.0004201387,0.0008665926,0.0009925388,0.0003826787],"domain_scores_gemma":[0.9983172,0.0001768491,0.0003343216,0.0004445173,0.0004491105,0.0002780254],"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":[0.00007535339,0.00002918729,0.0004847692,0.000004593856,0.00004354318,0.0000273464,0.001612067,0.7441074,0.0004759383,0.2499907,0.00002037152,0.003128778],"study_design_scores_gemma":[0.0006569013,0.002055463,0.000238869,0.00004920723,0.000008156555,0.000006508388,0.0004741486,0.9927591,0.0002347711,0.0003573168,0.002810416,0.000349149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00100888,0.00001119464,0.8987529,0.008804753,0.0003144306,0.0001679049,7.591048e-7,0.0004824117,0.09045677],"genre_scores_gemma":[0.987827,0.00003211284,0.00730916,0.002323998,0.0002710194,0.00001440463,0.00008131791,0.00003269032,0.002108312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9868181,"threshold_uncertainty_score":0.99991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04466082375581626,"score_gpt":0.3204855486435333,"score_spread":0.275824724887717,"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."}}