{"id":"W2401533533","doi":"","title":"Off-policy TD(λ) with a true online equivalence","year":2014,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Stability and Control of Uncertain Systems","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Online algorithm; Computer science; Equivalence (formal languages); Generalization; TRACE (psycholinguistics); Function approximation; Online learning; Algorithm; Function (biology); Artificial intelligence; Machine learning; Mathematics; Discrete mathematics; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002824217,0.0009890335,0.001344173,0.0005971142,0.0005562269,0.001918986,0.002507384,0.002296295,0.005900078],"category_scores_gemma":[0.01437617,0.0005575622,0.0009044041,0.0005795219,0.001674892,0.003153305,0.003358632,0.004012543,0.0009393892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00166384,"about_ca_system_score_gemma":0.002955783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004038473,"about_ca_topic_score_gemma":0.002759242,"domain_scores_codex":[0.9978834,0.0005427739,0.0001329873,0.0005879776,0.0006117551,0.0002411006],"domain_scores_gemma":[0.9942638,0.003274362,0.0003209987,0.001065788,0.0008210267,0.0002539687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004935339,0.0004319995,0.001775199,0.0002037191,0.00007596559,0.0001562832,0.0002672194,0.454337,0.005010171,0.1320229,0.004937098,0.4002889],"study_design_scores_gemma":[0.00003825256,0.0001125214,0.0001069807,0.0000104769,0.000008723946,0.00004693538,0.00001402645,0.970332,0.001840178,0.02624157,0.001237448,0.00001092155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009696391,0.00008326022,0.9866533,0.0001968172,0.00007352125,0.00007356165,0.0000479349,0.0005924188,0.002582791],"genre_scores_gemma":[0.5007933,0.0001121333,0.4912491,0.0006614611,0.0001204393,0.0002631058,0.0002715546,0.0003525582,0.006176333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005900078,"threshold_uncertainty_score":0.01973778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02643517356787296,"score_gpt":0.2660537146128079,"score_spread":0.2396185410449349,"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."}}