{"id":"W13294968","doi":"10.1016/0021-8707(56)90033-8","title":"Toward Off-Policy Learning Control with Function Approximation","year":2010,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":175,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Temporal difference learning; Function approximation; Approximation algorithm; Function (biology); Computer science; Linear approximation; Bellman equation; Optimal control; Extension (predicate logic); Mathematical optimization; Control (management); Artificial intelligence; Mathematics; Reinforcement learning; Artificial neural network; Nonlinear system","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":[0.0005058447,0.0002650122,0.0002032879,0.0004177853,0.0002742498,0.0006056678,0.0009147468,0.0001129475,0.0003406384],"category_scores_gemma":[0.0006329065,0.0002305235,0.00006914238,0.000303596,0.0000715315,0.0007366529,0.000141652,0.001760627,0.0002702002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000818189,"about_ca_system_score_gemma":0.0001684062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008420838,"about_ca_topic_score_gemma":0.00001520498,"domain_scores_codex":[0.9978631,0.0001563385,0.0003251315,0.000490737,0.0008307642,0.0003339077],"domain_scores_gemma":[0.9986272,0.000168478,0.0003697274,0.0003038158,0.0004149482,0.0001158616],"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":[0.0001057528,0.00003190959,0.009701381,0.000008544373,0.00006762356,0.00000943245,0.0003967693,0.5157424,0.003923931,0.4264555,0.00001624982,0.04354053],"study_design_scores_gemma":[0.001065407,0.0005315858,0.003423867,0.00004001716,0.000009685872,0.00003256329,0.00004897326,0.9786261,0.0001885119,0.0009824905,0.01478053,0.0002702108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0106375,0.000006076412,0.9326913,0.004855052,0.0006330823,0.0001860045,0.000001122295,0.0004629931,0.05052684],"genre_scores_gemma":[0.9877251,0.00001586709,0.007810126,0.000462858,0.0003230211,0.00002878056,0.00005251193,0.00002618901,0.003555513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9770876,"threshold_uncertainty_score":0.9400476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02266731972468504,"score_gpt":0.2706007747695721,"score_spread":0.247933455044887,"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."}}