{"id":"W2010124866","doi":"10.2316/journal.206.2006.2.206-2795","title":"FUZZY REINFORCEMENT LEARNING FOR EMBEDDED SOCCER AGENTS IN A MULTI-AGENT CONTEXT","year":2006,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Fuzzy logic; Context (archaeology); Artificial intelligence; Reinforcement; Machine learning; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0005142409,0.0001003471,0.0001430434,0.0002663276,0.00004814075,0.0002445049,0.0003389928,0.00004359551,0.000003639423],"category_scores_gemma":[0.0001739459,0.00009332858,0.00005761569,0.0001136969,0.00001681404,0.0005582566,0.00008785961,0.0001471828,0.000003173368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001359486,"about_ca_system_score_gemma":0.00007326648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000189726,"about_ca_topic_score_gemma":0.00000725642,"domain_scores_codex":[0.998686,0.00004557117,0.000592372,0.0001125156,0.0004288271,0.0001347535],"domain_scores_gemma":[0.9986573,0.00008075919,0.0005656063,0.00007082856,0.0005891662,0.00003638141],"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":[0.00001085559,0.00003772723,0.002155336,0.000008149954,0.00003090778,0.00000970397,0.0003935995,0.9575871,0.0001635104,0.03502841,0.0002194652,0.004355224],"study_design_scores_gemma":[0.001588454,0.0001135921,0.01453364,0.00009704919,0.000007267307,0.00002624761,0.00005809929,0.9813913,0.0001513034,0.0009143032,0.001023712,0.00009500883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007720734,0.00004978112,0.9899319,0.001137173,0.0007420119,0.000148044,2.835257e-7,0.00002053605,0.00024951],"genre_scores_gemma":[0.9138546,0.00004148812,0.08533664,0.0002403846,0.0000711937,0.000003786661,0.000009998437,0.00000717938,0.0004347459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9061338,"threshold_uncertainty_score":0.3805829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03483910685198837,"score_gpt":0.3084980660631231,"score_spread":0.2736589592111348,"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."}}