{"id":"W2150526575","doi":"10.1109/tai.2002.1180840","title":"Reinforcement learning in multiagent systems: a modular fuzzy approach with internal model capabilities","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Modular design; Computer science; Robustness (evolution); Fuzzy logic; Artificial intelligence; Multi-agent system; Fuzzy rule; Fuzzy control system; State space; Mathematics","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":[0.0007159676,0.000260503,0.0002764053,0.0002254793,0.000107188,0.0002814374,0.0006536544,0.00007285694,0.00001021861],"category_scores_gemma":[0.00009024979,0.0002073058,0.00005368659,0.0003136465,0.00006098209,0.000564706,0.0001775072,0.0003922088,0.00002291255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002591696,"about_ca_system_score_gemma":0.0001366751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002210775,"about_ca_topic_score_gemma":0.00000428398,"domain_scores_codex":[0.9976808,0.0001673225,0.0004919939,0.0005030522,0.0006295494,0.0005272342],"domain_scores_gemma":[0.9989549,0.00005748571,0.0001516577,0.0006201662,0.00009896279,0.0001168395],"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":[0.000006541833,0.00002837447,0.001747055,0.0000582856,0.00002027848,0.000006923266,0.001978918,0.8729959,0.00002387683,0.1230387,0.00002227895,0.00007277916],"study_design_scores_gemma":[0.0007301567,0.0001716437,0.00006270754,0.00006539327,0.000004619688,0.00002573861,0.001078531,0.9970807,0.00009836602,0.00008548034,0.0003144664,0.0002822373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007244702,0.00004240495,0.9221721,0.00003079996,0.00009749692,0.0004368552,6.503842e-8,0.0002050358,0.06977054],"genre_scores_gemma":[0.8720467,0.000008460594,0.1154791,0.00007947042,0.000009086956,0.00007722429,0.000002217077,0.00001793119,0.01227978],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.864802,"threshold_uncertainty_score":0.8453684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01905421074954002,"score_gpt":0.2220876135771597,"score_spread":0.2030334028276197,"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."}}