{"id":"W4386120402","doi":"10.1137/22m1515112","title":"Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games","year":2023,"lang":"en","type":"article","venue":"SIAM Journal on Mathematics of Data Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Satisficing; Reinforcement learning; Computer science; Mathematical economics; Convergence (economics); Multi-agent system; Mathematical optimization; Mathematics; Artificial intelligence; Economics","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":[0.005090278,0.0001681023,0.0002643533,0.0008002027,0.0002957416,0.0004029368,0.002653535,0.00003787916,0.000009267184],"category_scores_gemma":[0.002082336,0.0001418844,0.00002728417,0.001283691,0.000217242,0.001893863,0.001931975,0.0005155555,0.0000350412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009853833,"about_ca_system_score_gemma":0.0002433748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005593845,"about_ca_topic_score_gemma":0.000001742645,"domain_scores_codex":[0.996744,0.00005613508,0.0007337566,0.000420705,0.001559784,0.0004856719],"domain_scores_gemma":[0.9976904,0.0005395249,0.0005637755,0.0009174122,0.0001172958,0.0001716096],"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":[0.00000235808,0.00002525616,0.000236299,0.00004605043,0.000006953676,0.000028004,0.002401558,0.9801537,0.001335099,0.008564341,0.00003383911,0.007166562],"study_design_scores_gemma":[0.0003444236,0.0002057217,0.001721296,0.0004496714,0.00000511549,0.00006190273,0.0007176755,0.9951878,0.0002476629,0.0008690692,0.00004020522,0.0001495136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06393119,0.00003367887,0.9349955,0.0002225082,0.0002249414,0.0001977437,0.000001181294,0.00006142143,0.0003317813],"genre_scores_gemma":[0.9453029,0.0001524486,0.05436405,0.00003597414,0.00002121058,0.000002232171,0.00000278563,0.00001001525,0.0001083614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8813717,"threshold_uncertainty_score":0.5785879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05739997469785349,"score_gpt":0.321028057988703,"score_spread":0.2636280832908495,"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."}}