{"id":"W2403054493","doi":"10.1371/journal.pone.0180234","title":"A neural model of hierarchical reinforcement learning","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Air Force Office of Scientific Research; Ontario Innovation Trust","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Leverage (statistics); Transfer of learning; Artificial neural network; Reinforcement; Cognitive science; Machine learning; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003365504,0.000321591,0.0004233529,0.0002244703,0.0002643374,0.000647112,0.001258479,0.0008624233,0.004023445],"category_scores_gemma":[0.00108342,0.0002332248,0.0005041444,0.0002657669,0.0007346873,0.001100612,0.0005639744,0.0009013059,0.0003670443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010417,"about_ca_system_score_gemma":0.0009377848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008586951,"about_ca_topic_score_gemma":0.005909228,"domain_scores_codex":[0.9998469,0.00004282783,0.000006262155,0.00003892276,0.00003785599,0.00002707351],"domain_scores_gemma":[0.999777,0.00009442966,0.00003563471,0.00002385191,0.00003799182,0.00003101793],"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":[0.00002358532,0.00001811993,0.000350381,0.0000255266,0.00001640078,0.00005986896,0.0000604359,0.8961285,0.001946664,0.09395126,0.0005368569,0.00688243],"study_design_scores_gemma":[0.000006417946,0.000009595856,0.00007210446,0.000002398747,0.000002726759,0.00001147596,0.000003128654,0.9814451,0.0001007679,0.01799334,0.0003498876,0.000002994064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06833897,0.0003700999,0.9055836,0.001118509,0.00006876856,0.00004691197,0.0002448718,0.0004249712,0.02380341],"genre_scores_gemma":[0.9318518,0.0002617803,0.0578687,0.0001516545,0.00003328499,0.0001292395,0.00009768319,0.00003709026,0.009568793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008586951,"threshold_uncertainty_score":0.01707393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08724812942187102,"score_gpt":0.2616324953613466,"score_spread":0.1743843659394756,"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."}}