{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002982112,0.001169015,0.001024005,0.0006157054,0.0006310657,0.0009637548,0.001585587,0.00114429,0.002217718],"category_scores_gemma":[0.01643619,0.0006680883,0.0007906145,0.0004860193,0.002933462,0.002592826,0.001840221,0.002411651,0.0003051595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00145221,"about_ca_system_score_gemma":0.002008931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002790858,"about_ca_topic_score_gemma":0.002195109,"domain_scores_codex":[0.9981351,0.0009315382,0.00009024434,0.0003523503,0.000320027,0.0001707787],"domain_scores_gemma":[0.9906772,0.006972156,0.0008553746,0.0004517168,0.0006334509,0.0004100503],"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":[0.000149929,0.00009177413,0.001185486,0.00009188589,0.0000589416,0.0001173256,0.0002451038,0.7112673,0.001112075,0.2656595,0.0006270024,0.01939368],"study_design_scores_gemma":[0.00003258324,0.00006424916,0.00008139953,0.00001138481,0.000006513877,0.00002107112,0.00001565981,0.8607399,0.0004637664,0.1382037,0.0003502516,0.00000962753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03480444,0.000111778,0.9620788,0.0003087872,0.00002617887,0.00008027321,0.00004016465,0.0001250107,0.002424588],"genre_scores_gemma":[0.8441806,0.0002507783,0.1511887,0.0002041301,0.00004158696,0.0003070883,0.0001321969,0.00007488917,0.003620029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002982112,"threshold_uncertainty_score":0.01577109,"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."}}