{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001279181,0.0006478896,0.001498252,0.0005176004,0.0004144222,0.0006843343,0.001656453,0.001367408,0.003676849],"category_scores_gemma":[0.002029073,0.0003875181,0.000500193,0.0003439793,0.0007808998,0.0007144561,0.001228588,0.001211868,0.000612848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000756652,"about_ca_system_score_gemma":0.00124799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005323515,"about_ca_topic_score_gemma":0.003395457,"domain_scores_codex":[0.9996834,0.0001067961,0.0000159662,0.00006115581,0.00008841739,0.00004427572],"domain_scores_gemma":[0.999438,0.0002983596,0.00003198285,0.00003276791,0.0001505995,0.00004832587],"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":[0.0001999759,0.0001484749,0.0004265029,0.0001134794,0.00006174956,0.00008496899,0.0001018507,0.8091879,0.003056206,0.03469575,0.002280901,0.1496422],"study_design_scores_gemma":[0.00002207785,0.0000379693,0.00002545681,0.000004063843,0.000004592145,0.000008846562,0.000002622029,0.9975504,0.0001695064,0.001859573,0.0003109914,0.000003957299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009284125,0.0001352701,0.9880267,0.00009928626,0.00006143883,0.00005981105,0.00001329865,0.0002184605,0.002101598],"genre_scores_gemma":[0.5036252,0.0002118105,0.4879031,0.0001980058,0.00007006413,0.0003411198,0.00008259053,0.0001235414,0.007444488],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005323515,"threshold_uncertainty_score":0.01230031,"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."}}