{"id":"W1672238326","doi":"10.1109/ccece.2015.7129412","title":"The residual gradient FACL algorithm for differential games","year":2015,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Fuzzy logic; Algorithm; Convergence (economics); Computer science; Reinforcement learning; Residual; Fuzzy control system; Adaptive neuro fuzzy inference system; Control theory (sociology); Artificial intelligence; Mathematics; Control (management)","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":[0.0002870016,0.00009942463,0.0000868368,0.00003034285,0.0001957466,0.0003512046,0.0008720509,0.00003291599,0.000004824821],"category_scores_gemma":[0.00009106995,0.0000596932,0.00005015678,0.00009082814,0.00005162362,0.0001654719,0.0002751639,0.00007726522,0.00004588526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003703281,"about_ca_system_score_gemma":0.00005893835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001247665,"about_ca_topic_score_gemma":0.000003366237,"domain_scores_codex":[0.9989336,0.0000363606,0.0001763289,0.0002025164,0.0003422165,0.0003089696],"domain_scores_gemma":[0.9990917,0.0001773192,0.00006170057,0.0004467174,0.0001157961,0.0001067641],"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":[0.00001462096,0.00004995283,0.0001990626,0.000007491511,0.00008720386,0.000004590504,0.001877763,0.04217795,0.0000421306,0.3334037,0.1360736,0.4860619],"study_design_scores_gemma":[0.0004295685,0.0001943998,0.0002165352,0.000002746346,0.000004629415,0.000003370729,0.00008856149,0.9293089,0.0005065119,0.002017279,0.06711507,0.0001124094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003713534,0.00003306611,0.9940012,0.001250915,0.001069666,0.0002177115,7.12419e-7,0.0001482922,0.002907083],"genre_scores_gemma":[0.1510395,0.000032656,0.775356,0.0006427851,0.0007893058,0.0001294558,0.00001571406,0.00003667266,0.07195795],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.887131,"threshold_uncertainty_score":0.3386674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03577575525246496,"score_gpt":0.2697363551253321,"score_spread":0.2339605998728671,"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."}}