{"id":"W2188892596","doi":"10.13140/2.1.1456.2568","title":"True Online TD(λ)","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Equivalence (formal languages); Algorithm; TRACE (psycholinguistics); Function (biology); Simple (philosophy); Reinforcement learning; Online algorithm; Theoretical computer science; Artificial intelligence; Mathematics","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":[0.0001370585,0.00005934548,0.00006548301,0.00003820907,0.00004177265,0.00007709277,0.0005980468,0.00002484947,0.00006351434],"category_scores_gemma":[0.00006930761,0.00004838962,0.00002532152,0.0001286781,0.0000138737,0.0001763597,0.0001633719,0.00007253074,0.0003672242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001139385,"about_ca_system_score_gemma":0.00001175813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008480736,"about_ca_topic_score_gemma":0.000002566247,"domain_scores_codex":[0.9994037,0.0000251311,0.0001106393,0.000146873,0.0001611528,0.0001525229],"domain_scores_gemma":[0.9993813,0.00005881871,0.00003181755,0.0004494715,0.00002769446,0.00005087785],"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":[8.278192e-7,0.00002927018,0.001046667,0.000006948519,0.000008393969,0.000001731093,0.0001804891,0.3108442,0.0002593554,0.6345068,0.006370917,0.04674448],"study_design_scores_gemma":[0.0001160166,0.00005721064,0.00153557,0.000002871259,8.861955e-7,0.00000194661,0.000004434532,0.9333718,0.0002693578,0.000595726,0.06396655,0.00007766371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001580008,0.000002316058,0.9459564,0.0009397116,0.0002832055,0.00002980733,5.123999e-8,0.00023775,0.05097074],"genre_scores_gemma":[0.6865635,0.000002436697,0.2951725,0.001981641,0.0001083594,0.000001239944,0.000002481192,0.000006088598,0.01616178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6849835,"threshold_uncertainty_score":0.4720047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126392454971306,"score_gpt":0.2308848390242981,"score_spread":0.219620914474585,"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."}}