{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007898119,0.0003492701,0.0002498906,0.0001335527,0.0003363372,0.001708228,0.000396512,0.0001076954,0.0003515267],"category_scores_gemma":[0.0003143878,0.0002689434,0.0001517042,0.0003438516,0.0001008585,0.005139341,0.0001908374,0.000448758,0.001828941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003374146,"about_ca_system_score_gemma":0.00006154588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001622659,"about_ca_topic_score_gemma":2.689588e-7,"domain_scores_codex":[0.9979076,0.00005106184,0.0003793401,0.0006402264,0.000385219,0.0006365688],"domain_scores_gemma":[0.9989351,0.0002471967,0.0001699314,0.0003008529,0.00004898143,0.0002979166],"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":[0.002871132,0.001010496,0.01664381,0.0004541968,0.0001409382,0.0001212463,0.0002161592,0.559411,0.2721542,0.03033298,0.02505131,0.09159261],"study_design_scores_gemma":[0.0007501348,0.000452089,0.00009126404,0.00003302049,0.00001268722,0.00002488899,0.000004943611,0.9681354,0.006819009,0.004895897,0.01833647,0.0004441536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9582462,0.00001526077,0.01814545,0.00168754,0.0001187502,0.001667263,0.0004607407,0.0008245815,0.01883418],"genre_scores_gemma":[0.9765327,0.000003632098,0.0006322485,0.002142106,0.00008219656,0.0001819756,0.0003480467,0.0001075056,0.01996957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4087245,"threshold_uncertainty_score":0.9999763,"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."}}