{"id":"W3144252049","doi":"","title":"RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning.","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning","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":[0.004315979,0.002597443,0.001248329,0.001627397,0.0008238927,0.001568369,0.003612877,0.002024515,0.006673245],"category_scores_gemma":[0.02620866,0.0005629679,0.0009539207,0.001254606,0.001097595,0.001697106,0.001983081,0.003357156,0.002281766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001833885,"about_ca_system_score_gemma":0.002402892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01085448,"about_ca_topic_score_gemma":0.01664212,"domain_scores_codex":[0.9967495,0.001300585,0.0002753683,0.0005270828,0.0008043007,0.0003431504],"domain_scores_gemma":[0.9873049,0.007860404,0.0005483033,0.002104637,0.001559544,0.0006221647],"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":[0.001720613,0.001788027,0.003589473,0.001443894,0.0003040172,0.0002880611,0.0001659248,0.7038658,0.002863432,0.01441304,0.07887872,0.1906791],"study_design_scores_gemma":[0.0002369867,0.0004212072,0.001214087,0.00008919759,0.00003485746,0.0000906433,0.00005234592,0.9704902,0.003777235,0.01695333,0.006608001,0.00003190621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.2582255,0.01034047,0.5760539,0.002578509,0.002067448,0.001525613,0.02734694,0.03655652,0.08530521],"genre_scores_gemma":[0.7069229,0.001097239,0.252745,0.0005340432,0.0001733021,0.001342021,0.02485417,0.002749137,0.009582235],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01085448,"threshold_uncertainty_score":0.0228253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02519742502517128,"score_gpt":0.2518586570634151,"score_spread":0.2266612320382439,"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."}}