{"id":"W4285605296","doi":"10.24963/ijcai.2022/65","title":"Exploring the Benefits of Teams in Multiagent Learning","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Incentive; Multi-agent system; Computer science; Knowledge management; Reinforcement learning; Population; Social learning; Artificial intelligence; Management science; Engineering; Sociology; Microeconomics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0012055,0.0001437806,0.0002146552,0.0001624731,0.0007786689,0.00007126462,0.001222366,0.00002669064,0.0002901183],"category_scores_gemma":[0.0006221273,0.0001125924,0.0001320137,0.0003570977,0.0004810227,0.0002787067,0.0007139215,0.0004752586,0.00001468359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004195384,"about_ca_system_score_gemma":0.00007799457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003007679,"about_ca_topic_score_gemma":0.0009453815,"domain_scores_codex":[0.9980742,0.00004900178,0.0006234279,0.0002820163,0.0007199398,0.000251428],"domain_scores_gemma":[0.9987912,0.0001401719,0.0006145791,0.0001006208,0.0003149247,0.00003852336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001180722,0.0003105635,0.01370393,0.00001056726,0.00002872787,3.686958e-7,0.05491131,0.006313863,0.007158435,0.9041666,0.00002950952,0.01324802],"study_design_scores_gemma":[0.0001807637,0.0005033967,0.01924732,0.000563819,0.00003558382,0.000004088186,0.4721237,0.008036233,0.4487836,0.04708151,0.002794012,0.0006460294],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9702889,0.00003420911,0.000008970947,0.006989894,0.001008557,0.0003897165,0.00001183085,0.00002427516,0.0212437],"genre_scores_gemma":[0.9990407,0.0002572643,0.00008540999,0.00007094577,0.00007770481,0.0001900674,8.517495e-7,0.00001152168,0.0002655201],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8570851,"threshold_uncertainty_score":0.598897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2138455794608266,"score_gpt":0.3363991438027922,"score_spread":0.1225535643419657,"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."}}