{"id":"W2169300227","doi":"10.48550/arxiv.1504.05539","title":"Temporal-Difference Networks","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Generalization; Temporal difference learning; Artificial intelligence; Machine learning; Set (abstract data type); Markov process; Class (philosophy); Interval (graph theory); Range (aeronautics); Mathematics; Reinforcement learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001998482,0.0001365604,0.0001323773,0.00007229226,0.00008702413,0.00008714142,0.00102831,0.00007316475,0.00000698264],"category_scores_gemma":[0.00002236827,0.0001415786,0.00005193935,0.0005985172,0.00006257995,0.0003952738,0.0002676923,0.0001749859,0.0001334725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005986264,"about_ca_system_score_gemma":0.000110807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001001558,"about_ca_topic_score_gemma":0.00001803022,"domain_scores_codex":[0.9989907,0.00007285364,0.0001028243,0.0004791704,0.00006438708,0.0002901265],"domain_scores_gemma":[0.9988843,0.00003717786,0.00006341336,0.0005831106,0.0001371055,0.0002949057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002183681,0.00008712143,0.01262779,0.000004724911,0.00002059857,0.0002373787,0.0002546595,0.2080278,0.00002647856,0.7713186,0.002050555,0.005322432],"study_design_scores_gemma":[0.0002845542,0.00006209561,0.0006038146,0.00001107476,0.000005974162,0.000006674678,0.00003311385,0.9584815,0.00002880887,0.039882,0.0004021823,0.0001982146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06905765,0.00004408856,0.9263939,0.0001089509,0.0002372093,0.00004960967,5.821219e-7,0.0002631441,0.00384492],"genre_scores_gemma":[0.994548,0.00001921417,0.002954573,0.0002721832,0.00004470463,2.277965e-7,0.000001811758,0.000006012352,0.00215333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9254903,"threshold_uncertainty_score":0.577341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1299207618721676,"score_gpt":0.1878619261903546,"score_spread":0.05794116431818694,"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."}}