{"id":"W1784946991","doi":"","title":"Empirically Evaluating Multiagent Reinforcement Learning Algorithms","year":2005,"lang":"en","type":"article","venue":"","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Regret; Artificial intelligence; Convergence (economics); Variety (cybernetics); Machine learning; Test (biology); Nash equilibrium; Mathematical optimization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02072019,0.001526961,0.001146289,0.001575487,0.0008251608,0.001341773,0.002214493,0.002174962,0.001162927],"category_scores_gemma":[0.08407617,0.0004834516,0.0005180484,0.0009849647,0.001410535,0.00222893,0.001734452,0.002084579,0.0002927386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002196836,"about_ca_system_score_gemma":0.001410448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00292726,"about_ca_topic_score_gemma":0.003156223,"domain_scores_codex":[0.9834409,0.01280061,0.0007954145,0.0009118872,0.001600824,0.0004503565],"domain_scores_gemma":[0.8741024,0.1118845,0.003917028,0.005096401,0.00377428,0.001225434],"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":[0.001039753,0.002540323,0.01753631,0.0003688708,0.0002743443,0.00007815033,0.0002241981,0.9208204,0.001205966,0.007363281,0.001717003,0.04683153],"study_design_scores_gemma":[0.0002649372,0.0009638379,0.001657737,0.00003678304,0.00002852651,0.00002835209,0.0001014135,0.9883689,0.001348092,0.006539968,0.0006434143,0.00001801358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8513263,0.002503257,0.1341405,0.00125357,0.000197642,0.0008192146,0.000440813,0.0005935092,0.008725269],"genre_scores_gemma":[0.9499575,0.0002009058,0.04848626,0.0001155035,0.00003772717,0.0003637487,0.0003495441,0.0000358941,0.0004528364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02072019,"threshold_uncertainty_score":0.1095802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2610912538203148,"score_gpt":0.4943785065925657,"score_spread":0.2332872527722508,"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."}}