{"id":"W4360764815","doi":"10.1109/icmla55696.2022.00044","title":"Benchmarking Offline Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Benchmarking; Reinforcement learning; Computer science; Hyperparameter; Machine learning; Artificial intelligence; Offline learning; Performance improvement; Online learning; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005933325,0.0001153943,0.0001118301,0.0001366981,0.000673566,0.0001235732,0.0009513476,0.00001652567,0.001712451],"category_scores_gemma":[0.00003844792,0.0001192636,0.00006055739,0.0004578653,0.00001530175,0.0002768469,0.001621224,0.0004096977,0.00007946304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384361,"about_ca_system_score_gemma":0.00005637481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002176955,"about_ca_topic_score_gemma":3.937228e-7,"domain_scores_codex":[0.9983526,0.0000962123,0.000274068,0.0002891947,0.0006523338,0.0003355777],"domain_scores_gemma":[0.9992661,0.00007686581,0.0001282616,0.0004257746,0.00003578526,0.00006718489],"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":[0.000001760805,0.000006759134,0.0006692787,0.000002959626,0.000009324734,0.000008557305,0.0002894157,0.9428643,0.00009206019,0.05084478,0.001256231,0.003954538],"study_design_scores_gemma":[0.000185525,0.0002560272,0.0001676873,0.000002192011,0.000002196032,0.00001364318,0.00006636833,0.8755998,0.0001058351,0.00006890354,0.1233872,0.0001446326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005493773,0.00001671466,0.9260619,0.0004211661,0.0004799569,0.0001123708,4.349621e-8,0.0003438508,0.07201459],"genre_scores_gemma":[0.934501,0.000006291603,0.03840866,0.0009006527,0.00007152223,0.00003247211,0.00001182634,0.00001107987,0.02605652],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9339516,"threshold_uncertainty_score":0.9992001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0137320246154256,"score_gpt":0.2294180182797683,"score_spread":0.2156859936643427,"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."}}