{"id":"W4224220194","doi":"10.1016/j.neunet.2022.03.037","title":"Deep learning, reinforcement learning, and world models","year":2022,"lang":"en","type":"review","venue":"Neural Networks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":493,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Session (web analytics); Human intelligence; Deep learning; Cognitive science; Reinforcement; Psychology","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":[0.000564371,0.0008358652,0.0008830496,0.001251639,0.0002000842,0.0009371378,0.0007494772,0.001239888,0.002299385],"category_scores_gemma":[0.001046926,0.0002989797,0.0004019927,0.001709689,0.000669213,0.001669053,0.0005843914,0.00177481,0.0008937926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007439223,"about_ca_system_score_gemma":0.001206911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001635076,"about_ca_topic_score_gemma":0.001696876,"domain_scores_codex":[0.9998467,0.0000387959,0.00001455686,0.00003085355,0.0000552343,0.00001392824],"domain_scores_gemma":[0.9996673,0.0002139531,0.00003123653,0.00001119776,0.00005681988,0.00001951411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004622967,0.00007555014,0.0002889558,0.01118022,0.0001109204,0.0001194841,0.00006306879,0.005105667,0.0006332055,0.04952654,0.02633995,0.9065102],"study_design_scores_gemma":[0.00002181617,0.0001145086,0.0009933925,0.00525447,0.000133071,0.0007494107,0.00006992096,0.003872494,0.0008567607,0.06209995,0.9257832,0.00005104932],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000266991,0.9915149,0.003327353,0.001069738,0.0002749429,0.000008070853,0.00002741005,0.00002227826,0.003488287],"genre_scores_gemma":[0.00487364,0.9923897,0.001078806,0.0003699147,0.0002951008,0.00001690327,0.0000457823,0.000003960376,0.000926211],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002299385,"threshold_uncertainty_score":0.007692277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04696882901226523,"score_gpt":0.2927112085831605,"score_spread":0.2457423795708953,"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."}}