{"id":"W3162022061","doi":"10.48550/arxiv.2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Task (project management); Composition (language); Generalization; Resource (disambiguation); Team composition; Artificial intelligence; Human–computer interaction; Distributed computing; Knowledge management; Mathematics; Engineering","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":[0.001925867,0.000989585,0.001257291,0.000398651,0.000581664,0.0006329067,0.001938496,0.001272144,0.001886898],"category_scores_gemma":[0.004945704,0.000503097,0.0004607535,0.0003300895,0.001188634,0.0009710815,0.001587555,0.001846863,0.0003608366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044209,"about_ca_system_score_gemma":0.001253522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005974941,"about_ca_topic_score_gemma":0.004377205,"domain_scores_codex":[0.9993831,0.0002513515,0.00002446525,0.0001448593,0.000109198,0.00008702029],"domain_scores_gemma":[0.9978803,0.001276277,0.0001930882,0.0001760219,0.0002667096,0.0002076408],"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":[0.00007009973,0.00006875266,0.0005967183,0.00003208089,0.0000379284,0.00004081953,0.00005198198,0.9723136,0.000710169,0.005318451,0.0005662431,0.02019318],"study_design_scores_gemma":[0.000004626692,0.000008977097,0.00001861013,0.000001109833,0.000001346277,0.000002649798,0.000002202852,0.9985698,0.00008689378,0.001231683,0.00007082208,0.000001106446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02344307,0.0001738139,0.9743373,0.0001846736,0.00003976296,0.00004323389,0.000016616,0.0003501843,0.001411206],"genre_scores_gemma":[0.90401,0.00008840458,0.09295513,0.0001410928,0.00003503016,0.0001492605,0.00006370119,0.0000784498,0.002478908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005974941,"threshold_uncertainty_score":0.01188034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06769760757836442,"score_gpt":0.2185804099017773,"score_spread":0.1508828023234129,"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."}}