{"id":"W2588293788","doi":"10.1007/s40815-016-0284-8","title":"A Residual Gradient Fuzzy Reinforcement Learning Algorithm for Differential Games","year":2017,"lang":"en","type":"article","venue":"International Journal of Fuzzy Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Algorithm; Residual; Computer science; Weighted Majority Algorithm; Convergence (economics); Fuzzy logic; Artificial intelligence; Mathematics; Mathematical optimization; Wake-sleep algorithm; Artificial neural network; Generalization error","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007938656,0.0001733603,0.0003195744,0.0002384487,0.0002826632,0.00119688,0.002704629,0.00006314085,0.00000212375],"category_scores_gemma":[0.0003473727,0.0001456131,0.0002367818,0.00002946741,0.00006879555,0.0008060453,0.0003242718,0.0002469877,0.000007312574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002428324,"about_ca_system_score_gemma":0.0001297287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007767003,"about_ca_topic_score_gemma":0.00000418198,"domain_scores_codex":[0.997686,0.00008414678,0.0007125905,0.0002329709,0.0009955635,0.000288689],"domain_scores_gemma":[0.9965863,0.0001558743,0.001609883,0.0003654852,0.001149534,0.0001329753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002828223,0.000268897,0.002138134,0.00004586506,0.002197987,0.0004676587,0.00180165,0.009310816,0.001473935,0.1631846,0.003132235,0.8156954],"study_design_scores_gemma":[0.005935461,0.001249646,0.004563272,0.0005645682,0.00007453244,0.0008342367,0.0002731917,0.9499681,0.0002590768,0.004243817,0.03154238,0.0004917098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005271317,0.0002130235,0.984767,0.001102725,0.007536478,0.0002816671,0.000007576497,0.00003380097,0.0007863859],"genre_scores_gemma":[0.9806486,0.00002065453,0.01636706,0.00003118543,0.001790008,0.00002768865,0.000004806814,0.0000139255,0.001096035],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9753773,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01861807992229806,"score_gpt":0.2851494187181415,"score_spread":0.2665313387958434,"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."}}