{"id":"W3166318878","doi":"","title":"Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition","year":2021,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":8,"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; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000450351,0.0003031398,0.0004686783,0.0004648312,0.0004748889,0.00008473921,0.0007243238,0.0004118048,0.000006039024],"category_scores_gemma":[0.0002937277,0.0003139528,0.0002101016,0.0009220784,0.000277237,0.0002340354,0.0004961845,0.0005264799,0.00003890148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001962938,"about_ca_system_score_gemma":0.0001907007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008763802,"about_ca_topic_score_gemma":0.00001065979,"domain_scores_codex":[0.9977447,0.00003834808,0.0006620151,0.0007106067,0.0002876901,0.0005565763],"domain_scores_gemma":[0.9982281,0.00003889936,0.0003271862,0.0008919158,0.0003884063,0.0001255056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006655294,0.0006678334,0.001010751,0.0006480372,0.0002845562,0.0001852018,0.0004559127,0.1674187,0.5201179,0.1328338,0.001056108,0.1752546],"study_design_scores_gemma":[0.001224891,0.000212449,0.00004746732,0.000299279,0.00005033182,0.0001660051,0.0001541149,0.6479098,0.2514932,0.001513799,0.09645835,0.0004703865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0768684,0.0002885396,0.9192312,0.001391919,0.0007618429,0.000459969,0.00001136776,0.0007677017,0.000219105],"genre_scores_gemma":[0.7958542,0.00004144846,0.2035042,0.0001066951,0.00002340001,0.00008790967,0.00006823877,0.00002380667,0.0002900514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7189858,"threshold_uncertainty_score":0.9999313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01678793028330439,"score_gpt":0.262349410814342,"score_spread":0.2455614805310376,"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."}}