{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003619045,0.0008188441,0.001300474,0.0005332871,0.0006055829,0.001356811,0.001473155,0.001418815,0.001988105],"category_scores_gemma":[0.01254282,0.0004744629,0.0005035323,0.0005072035,0.002103292,0.001948848,0.001472119,0.00159877,0.000245501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002161033,"about_ca_system_score_gemma":0.001550781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004540205,"about_ca_topic_score_gemma":0.00268287,"domain_scores_codex":[0.9976012,0.00140005,0.0001032263,0.0003539867,0.0003436097,0.0001980148],"domain_scores_gemma":[0.994487,0.003727804,0.0007078103,0.0003566584,0.0004176493,0.0003031844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000543887,0.000042328,0.0006758061,0.00006389393,0.00004876344,0.000088577,0.0001094675,0.8339559,0.0003766966,0.1523113,0.0007663328,0.01150664],"study_design_scores_gemma":[0.00002579725,0.00002763893,0.00009299468,0.000008498881,0.000005734738,0.00001326496,0.00001434796,0.9103865,0.00009609949,0.08871157,0.0006115094,0.000006081737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02689666,0.0006783149,0.964097,0.0008554659,0.00006469394,0.00006381979,0.00004138477,0.0001860411,0.0071167],"genre_scores_gemma":[0.9197851,0.0004053234,0.07639956,0.0001846813,0.00006619878,0.0002216131,0.00005043968,0.000040997,0.002845961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004540205,"threshold_uncertainty_score":0.01913959,"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."}}