{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002936141,0.001629104,0.001860193,0.000838263,0.0005538244,0.00166337,0.002049875,0.001860138,0.003300941],"category_scores_gemma":[0.008435267,0.0007002832,0.0009506204,0.0006141168,0.002189066,0.001531674,0.002789471,0.003554289,0.0007983472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002037738,"about_ca_system_score_gemma":0.002279104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00585327,"about_ca_topic_score_gemma":0.002625465,"domain_scores_codex":[0.9987147,0.0003347325,0.00006135148,0.0002539192,0.0004526936,0.000182676],"domain_scores_gemma":[0.9964526,0.002346283,0.0002544181,0.0002799712,0.0005250287,0.0001417132],"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":[0.0001153535,0.0001036054,0.0004194267,0.00009093137,0.00003236252,0.00005908406,0.0001201643,0.8669133,0.001411857,0.05506869,0.001403967,0.07426123],"study_design_scores_gemma":[0.000007179633,0.00001931516,0.00001368817,0.000006413277,0.000001903528,0.000005895445,0.000002909148,0.991289,0.0002004786,0.008099364,0.0003509354,0.000002805635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003765274,0.0001377512,0.9931476,0.0001473179,0.00003939305,0.0000352694,0.00001391504,0.0003708324,0.002342661],"genre_scores_gemma":[0.6216077,0.0003366968,0.3683889,0.0007247206,0.0001374821,0.0004586868,0.0001837131,0.0004023894,0.007759728],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00585327,"threshold_uncertainty_score":0.01552796,"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."}}