{"id":"W2269274350","doi":"10.48550/arxiv.1512.04087","title":"True Online Temporal-Difference Learning","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Temporal difference learning; Computer science; Artificial intelligence; Equivalence (formal languages); Lambda; Reinforcement learning; Domain (mathematical analysis); Online learning; Machine learning; Binary number; Online algorithm; Simple (philosophy); Algorithm; Theoretical computer science; Mathematics; Discrete mathematics; Arithmetic; Mathematical analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003859187,0.0004411497,0.0004578537,0.0003177009,0.0001832389,0.0002423038,0.003101722,0.0003905428,0.00003031432],"category_scores_gemma":[0.0001916978,0.0005050108,0.0001920367,0.0006261503,0.0001250052,0.0003462346,0.003976226,0.001667425,0.0002107599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003518579,"about_ca_system_score_gemma":0.0004753979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001714262,"about_ca_topic_score_gemma":0.00002152214,"domain_scores_codex":[0.9974765,0.0002639714,0.0003089161,0.00121972,0.0002231929,0.0005077614],"domain_scores_gemma":[0.9971901,0.0001219507,0.0004997196,0.001534038,0.0003465106,0.00030773],"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":[0.00001001973,0.00004350445,0.009164898,0.0000463883,0.0000504024,0.0001913153,0.0002606249,0.9731921,0.00001052972,0.01620984,0.0002463851,0.0005739789],"study_design_scores_gemma":[0.0004271757,0.0001144265,0.00155466,0.0001137072,0.00003861994,0.000004278937,0.00008940614,0.9891911,0.00001620672,0.005512863,0.002377296,0.0005602656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1234524,0.00004121028,0.8714485,0.0001061001,0.0007169494,0.0002203947,0.000004928517,0.0006113814,0.003398115],"genre_scores_gemma":[0.9719549,0.000101537,0.007016428,0.00008260691,0.0001156593,5.301028e-7,0.00008622509,0.00002883824,0.0206133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.864432,"threshold_uncertainty_score":0.9997401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1219179917530586,"score_gpt":0.2099222055253362,"score_spread":0.08800421377227757,"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."}}