{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001467294,0.001076314,0.001008957,0.0003745649,0.0003866769,0.001197034,0.001525653,0.001163319,0.002753308],"category_scores_gemma":[0.003248612,0.0005618213,0.0006440381,0.0002802812,0.001555321,0.001945854,0.001931541,0.001807114,0.0004576615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008958358,"about_ca_system_score_gemma":0.0009118562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002565738,"about_ca_topic_score_gemma":0.00269954,"domain_scores_codex":[0.9994779,0.0001490618,0.00002623901,0.0001814213,0.00009735746,0.00006800847],"domain_scores_gemma":[0.9985917,0.0006595791,0.0001698764,0.0003428224,0.0001261111,0.0001098729],"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":[0.00005182831,0.00006454044,0.0005112384,0.00004309875,0.00003635695,0.0000303623,0.0000553553,0.9532869,0.002047725,0.007031178,0.0006844724,0.03615697],"study_design_scores_gemma":[0.00001114353,0.00002624036,0.0000628319,0.000004962107,0.000003951499,0.000006555206,0.000007519975,0.99302,0.0005937876,0.005912815,0.0003466988,0.000003452055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09408075,0.0002626105,0.8972369,0.0004323572,0.00003711855,0.0001228217,0.00007219477,0.001486596,0.006268593],"genre_scores_gemma":[0.8321809,0.0001479222,0.1641417,0.0001636541,0.00001895666,0.0001545626,0.000143842,0.0001147946,0.002933698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002753308,"threshold_uncertainty_score":0.009210765,"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."}}