{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001870706,0.0008401694,0.0008015399,0.000428549,0.0005042746,0.001634798,0.002720586,0.001535645,0.01095681],"category_scores_gemma":[0.009056724,0.0004127468,0.0006028966,0.000460146,0.000987036,0.002290642,0.002129858,0.002369988,0.002636039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00131391,"about_ca_system_score_gemma":0.003498855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004604914,"about_ca_topic_score_gemma":0.005405836,"domain_scores_codex":[0.9986743,0.0002964218,0.00008727753,0.0003950351,0.0003680578,0.0001789013],"domain_scores_gemma":[0.9959998,0.001860938,0.0002349914,0.001025619,0.0006796284,0.0001990185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005248004,0.0002901353,0.001679446,0.0002846593,0.00006096386,0.000129813,0.0001782418,0.1645452,0.004530951,0.08984771,0.02102568,0.7169024],"study_design_scores_gemma":[0.00008126262,0.000102773,0.0001883907,0.00002395356,0.00001726886,0.0001202814,0.00003115725,0.9356537,0.005286029,0.04954105,0.008932387,0.00002180028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006246683,0.0001113913,0.9865754,0.000240972,0.0001219111,0.00007964265,0.0001218292,0.002938485,0.003563699],"genre_scores_gemma":[0.3421736,0.000139534,0.6425018,0.0005953215,0.0001041277,0.0003033558,0.0005316951,0.0007365127,0.01291407],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01095681,"threshold_uncertainty_score":0.03665411,"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."}}