{"id":"W4409147637","doi":"10.1038/s41586-025-08744-2","title":"Mastering diverse control tasks through world models","year":2025,"lang":"en","type":"article","venue":"Nature","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scratch; Reinforcement learning; Artificial intelligence; Robustness (evolution); Normalization (sociology); Machine learning; Control (management); Programming language","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":[0.0001083024,0.0001190071,0.0001334028,0.0001042907,0.0001146002,0.0001571966,0.0008452351,0.000308915,0.00001782408],"category_scores_gemma":[0.00003312319,0.0001089347,0.00005783586,0.0004826373,0.0000232856,0.0006075017,0.0003238416,0.001318121,0.00003316811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005344386,"about_ca_system_score_gemma":0.000040385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006550568,"about_ca_topic_score_gemma":0.000004158499,"domain_scores_codex":[0.9990773,0.00002995524,0.0001387865,0.0002623063,0.0002507815,0.0002409028],"domain_scores_gemma":[0.999282,0.0000745033,0.00005521789,0.000491787,0.00006648724,0.00003000648],"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":[0.000005921775,0.000006528108,0.0002552389,0.00001561213,0.00002867042,0.00001152568,0.0002130953,0.7106743,0.00007508358,0.2791043,0.007707796,0.001901846],"study_design_scores_gemma":[0.0005848581,0.00001506467,0.0003253783,0.00006127568,0.00001131627,0.000001369819,0.00001835859,0.9420696,0.000187994,0.007151911,0.04943608,0.0001367663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001576711,0.0003004981,0.9303779,0.001965251,0.001013732,0.0001291125,0.000001081131,0.0001804664,0.06587429],"genre_scores_gemma":[0.9470498,0.000009184555,0.03301218,0.006174319,0.00005530898,0.000005678532,0.000001714396,0.000005952414,0.01368586],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9468921,"threshold_uncertainty_score":0.5726651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01599384051503829,"score_gpt":0.2703708969635651,"score_spread":0.2543770564485269,"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."}}