{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003584604,0.001083382,0.0009143619,0.0005724762,0.0008744919,0.003424035,0.001850317,0.003165564,0.007619202],"category_scores_gemma":[0.01386805,0.0004635453,0.000390664,0.000612266,0.003994334,0.008423558,0.002499212,0.008672443,0.001131431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002237679,"about_ca_system_score_gemma":0.001213309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001509513,"about_ca_topic_score_gemma":0.001077204,"domain_scores_codex":[0.9982877,0.0007985032,0.00005257446,0.0002120706,0.0005228274,0.0001263175],"domain_scores_gemma":[0.9909609,0.00668845,0.0002884717,0.0008350075,0.0008856789,0.000341529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001316221,0.00003939254,0.0001298706,0.0001062396,0.00002574065,0.00005015662,0.00005951267,0.02138823,0.0002662009,0.9258012,0.01111441,0.04088736],"study_design_scores_gemma":[0.00001905051,0.00002473404,0.00005234688,0.00005190446,0.000007512693,0.00003058945,0.00002137016,0.04732271,0.0003027758,0.9422253,0.00992963,0.00001217535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01170174,0.01840772,0.7229164,0.1381604,0.003970206,0.00003134859,0.0003446963,0.0003284664,0.1041391],"genre_scores_gemma":[0.8172453,0.01570472,0.09115303,0.0133509,0.01136165,0.000153054,0.0002284814,0.0003069441,0.05049587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007619202,"threshold_uncertainty_score":0.02548879,"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."}}