{"id":"W2407968944","doi":"","title":"A neural reinforcement learning model for tasks with unknown time delays","year":2013,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Ontario Innovation Trust","keywords":"Reinforcement learning; Markov decision process; Artificial intelligence; Computer science; Reinforcement; Task (project management); Function (biology); Machine learning; Psychology; Markov process; Mathematics; Engineering; Social 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":[0.0004273637,0.0004469391,0.0005058272,0.0002179004,0.0002541739,0.0006622305,0.001230997,0.001083686,0.003707163],"category_scores_gemma":[0.001406546,0.0002308789,0.0004158139,0.000276823,0.000618492,0.0009476308,0.0005509466,0.001073986,0.0004873243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009601337,"about_ca_system_score_gemma":0.0009287838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007972201,"about_ca_topic_score_gemma":0.006479668,"domain_scores_codex":[0.9998469,0.00004141513,0.000007783098,0.00004006711,0.00003788098,0.00002591814],"domain_scores_gemma":[0.9997038,0.0001522065,0.00004079903,0.0000187103,0.00005537255,0.00002907279],"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":[0.00003217601,0.00002274618,0.0002382583,0.00002264381,0.00001011965,0.00005598312,0.00003306462,0.9585742,0.0009134046,0.03260163,0.0005166039,0.006979184],"study_design_scores_gemma":[0.000006521517,0.00000952945,0.00003825148,0.000002132522,0.00000244188,0.000008462593,0.000002194899,0.9916801,0.00007512476,0.007862209,0.0003106046,0.000002413323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04599464,0.0003602176,0.9380929,0.0009558117,0.00009760484,0.00004707616,0.0002507547,0.0003262541,0.01387473],"genre_scores_gemma":[0.9143769,0.0003805796,0.0679065,0.0001576967,0.00004983561,0.0002355301,0.0001722533,0.00004101246,0.01667978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007972201,"threshold_uncertainty_score":0.01585162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01779342405435669,"score_gpt":0.2060740220936673,"score_spread":0.1882805980393107,"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."}}