{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003764953,0.0001754518,0.000270967,0.0001668001,0.0002712623,0.0003930593,0.0004740007,0.00009256174,0.00000697671],"category_scores_gemma":[0.0003336411,0.0001646888,0.00007715185,0.0007095922,0.00003135724,0.002902739,0.000105559,0.0002010849,0.00001412631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007278322,"about_ca_system_score_gemma":0.0001457329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001849689,"about_ca_topic_score_gemma":2.168776e-7,"domain_scores_codex":[0.998017,0.0000501561,0.0009835968,0.0001720579,0.0005154193,0.0002618161],"domain_scores_gemma":[0.998063,0.00007552397,0.0009936513,0.0001838427,0.0005769756,0.000106966],"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":[0.00002847638,0.000004536911,0.000176305,0.0008822675,0.00001174838,1.638518e-7,0.003461677,0.9868777,0.0001874606,0.001662802,0.002719781,0.003987055],"study_design_scores_gemma":[0.0006391085,0.0004868511,0.00004050613,0.00009088617,0.000009874927,0.000006872939,0.000305868,0.9728975,0.000961313,0.000005837886,0.02439297,0.0001623628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009418303,0.00005837385,0.9936435,0.0007770068,0.0004284522,0.0007367727,0.000001158043,0.0002303901,0.003182465],"genre_scores_gemma":[0.9944941,0.000006487978,0.004457987,0.0004200029,0.00009866466,0.00007647477,0.00009373287,0.00000902856,0.0003435226],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9935523,"threshold_uncertainty_score":0.6715816,"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."}}