{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006544319,0.000849761,0.001538543,0.0004786976,0.0008028433,0.0006343161,0.001825254,0.0002887159,0.0004274015],"category_scores_gemma":[0.0000839915,0.0007896046,0.0004854276,0.001255128,0.00009776878,0.0005656304,0.002701472,0.004223017,0.00003438108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002440002,"about_ca_system_score_gemma":0.00007803505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001270443,"about_ca_topic_score_gemma":0.000003855707,"domain_scores_codex":[0.9951777,0.0007663104,0.001052129,0.00114287,0.000840757,0.001020177],"domain_scores_gemma":[0.9971245,0.0006886589,0.001030476,0.0008201958,0.00004532849,0.0002908426],"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":[0.000001082722,0.000003684602,0.000003175718,0.0004128048,0.00004322454,0.00002399019,0.00004199343,0.5494549,9.859455e-10,0.001698198,0.0002604373,0.4480565],"study_design_scores_gemma":[0.0000856254,0.0001317514,1.42694e-7,0.0003327031,0.00008425572,0.00003854027,0.000003243852,0.5022877,3.250746e-9,0.00001732846,0.4966387,0.0003799662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.683847e-8,0.5497999,0.442696,0.00001436089,0.0006205231,0.000438554,7.871848e-8,0.000338992,0.006091516],"genre_scores_gemma":[0.0000861663,0.9745811,0.001226661,0.0001547552,0.0003219173,0.0001772599,0.0001121679,0.0001124396,0.02322754],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4963783,"threshold_uncertainty_score":0.9994555,"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."}}