{"id":"W2128643385","doi":"10.1145/860575.860689","title":"Coordination in multiagent reinforcement learning","year":2003,"lang":"en","type":"article","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":158,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Bayesian probability; Q-learning; Artificial intelligence; Multi-agent system; Mathematical optimization; Machine learning; Mathematics; 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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001772065,0.0000380498,0.00005656612,0.0001191609,0.00009936255,0.00004277594,0.0001063656,0.00002104928,0.003873005],"category_scores_gemma":[0.001301487,0.00002859029,0.00002373627,0.0004759836,0.00001985317,0.0001317019,0.00001421176,0.00006416042,0.001075682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002467589,"about_ca_system_score_gemma":0.00001288403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009423971,"about_ca_topic_score_gemma":0.00001411605,"domain_scores_codex":[0.9990842,0.0001313958,0.0002655058,0.0001531534,0.0002830089,0.00008272166],"domain_scores_gemma":[0.9994354,0.000250864,0.00006706305,0.0001505607,0.00006484437,0.00003132755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000407788,0.00003943332,0.01232537,3.902639e-7,0.00000165281,5.119658e-7,0.0004453571,0.08707418,0.000846322,0.8808025,0.002738902,0.01572135],"study_design_scores_gemma":[0.0006616681,0.00004338049,0.0101826,0.000003877127,0.00000222294,0.000004462547,0.005731382,0.05240624,0.01094655,0.1503369,0.7695012,0.0001795418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1908185,0.00001287204,0.5317374,0.001101885,0.0001184322,0.0002001938,1.192712e-7,0.00004514355,0.2759654],"genre_scores_gemma":[0.9309018,0.000001066143,0.0005520671,0.0001004662,0.000006319324,0.00001930102,7.512781e-7,0.000001765788,0.06841645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7667623,"threshold_uncertainty_score":0.9997021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09739506435622934,"score_gpt":0.3936254330244737,"score_spread":0.2962303686682444,"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."}}