{"id":"W359568995","doi":"","title":"A convergent O ( n ) algorithm for off-policy temporal-difference learning with linear function approximation","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Temporal difference learning; Markov decision process; Algorithm; Stochastic approximation; Function (biology); Reinforcement learning; Stochastic gradient descent; Markov process; Mathematics; Quadratic equation; Approximation algorithm; Norm (philosophy); Computer science; Function approximation; Mathematical optimization; Applied mathematics; Artificial intelligence; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001814665,0.000168045,0.0001626731,0.0001541893,0.0003228672,0.00006627512,0.0003262472,0.00006531212,0.00001912699],"category_scores_gemma":[0.00006959923,0.0001335624,0.00005151051,0.0004188903,0.00005308939,0.0003923725,0.00008964076,0.0001664494,0.00005295117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007055081,"about_ca_system_score_gemma":0.0001779047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004798926,"about_ca_topic_score_gemma":0.000001435478,"domain_scores_codex":[0.9986966,0.00004415103,0.0002529185,0.0003455084,0.0003602682,0.000300558],"domain_scores_gemma":[0.9991305,0.00007789039,0.0001778691,0.0003132667,0.0002092476,0.00009122711],"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":[0.00004814753,0.00009628459,0.006016062,0.00006157948,0.00008575082,0.000008028179,0.001479441,0.6766451,0.0003322593,0.01790076,0.0007215899,0.296605],"study_design_scores_gemma":[0.0006507232,0.0006401619,0.001450273,0.00001361199,0.000006302272,0.00002383586,0.00003284213,0.988685,0.0005460291,0.00008043269,0.007679178,0.0001915766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001831732,0.0000159449,0.995727,0.0002553173,0.0001451855,0.0004144938,3.886671e-7,0.0003927519,0.001217196],"genre_scores_gemma":[0.1858481,0.00004416417,0.7929378,0.0003307465,0.0002120807,0.00008570671,0.00003974153,0.00002366077,0.02047802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.31204,"threshold_uncertainty_score":0.5446516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02640782854945645,"score_gpt":0.2470170740798348,"score_spread":0.2206092455303784,"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."}}