{"id":"W3214251933","doi":"","title":"A Minimalist Approach to Offline Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Leverage (statistics); Hyperparameter; Offline learning; Artificial intelligence; Machine learning; Online algorithm; Algorithm; Online 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003673095,0.0001579628,0.0001909189,0.0001788459,0.0002207346,0.001558338,0.0006226086,0.0000618116,0.000002155165],"category_scores_gemma":[0.0001894694,0.0001493782,0.00003532667,0.0007530973,0.00001616442,0.004091626,0.0003519015,0.0001684952,0.00006179308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007811743,"about_ca_system_score_gemma":0.0001301377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000320627,"about_ca_topic_score_gemma":4.128341e-7,"domain_scores_codex":[0.9983774,0.00005940496,0.0005929953,0.0002301393,0.0004663797,0.0002736668],"domain_scores_gemma":[0.9987475,0.00002225662,0.000283321,0.0004273637,0.0004057163,0.0001138441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005116647,0.0002258064,0.0009384174,0.003538405,0.00006408936,0.00003652716,0.03220778,0.2625124,0.003216789,0.09070986,0.06704326,0.5394555],"study_design_scores_gemma":[0.0001675641,0.00007189308,0.0000891969,0.0001461454,0.000003856539,0.0001563276,0.0004702542,0.9139947,0.001897393,0.00001384485,0.08276188,0.0002269466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002141961,0.00007407402,0.9645148,0.0003632607,0.0002382745,0.0002568112,0.000002889944,0.0008675569,0.03154039],"genre_scores_gemma":[0.9230214,0.000002337871,0.07497847,0.0007852377,0.00006940483,0.0001093859,0.0001622591,0.00000856117,0.0008629716],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9208794,"threshold_uncertainty_score":0.9994782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02581352480745651,"score_gpt":0.2637669248935865,"score_spread":0.23795340008613,"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."}}