{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001966037,0.001075036,0.001331192,0.0004371714,0.0006766804,0.0006988422,0.002156593,0.001388667,0.00214557],"category_scores_gemma":[0.005186487,0.0005571736,0.0005125397,0.0003561394,0.001174662,0.001030136,0.001667195,0.001919069,0.0004082813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001098534,"about_ca_system_score_gemma":0.001435777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00745633,"about_ca_topic_score_gemma":0.005891714,"domain_scores_codex":[0.9993458,0.0002550162,0.00002548104,0.000165952,0.0001130385,0.0000946824],"domain_scores_gemma":[0.9977524,0.001371961,0.0002044162,0.0001675104,0.0002751487,0.0002286336],"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":[0.00007723202,0.00007561827,0.0006912429,0.00003667574,0.00004335573,0.00004848624,0.00006146773,0.9721422,0.0007122511,0.00532948,0.0006707834,0.02011123],"study_design_scores_gemma":[0.000005512433,0.000009081171,0.00002086721,0.000001272197,0.000001605933,0.000002748254,0.000002776167,0.9985429,0.00007722191,0.001249781,0.00008482576,0.000001303986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02409826,0.0002097533,0.9732152,0.0002275934,0.00005318435,0.00005420322,0.00002270231,0.0003858295,0.001733168],"genre_scores_gemma":[0.9013979,0.0001015462,0.09493691,0.0001863364,0.00004439347,0.0001682508,0.00007813373,0.00008503196,0.003001544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00745633,"threshold_uncertainty_score":0.01482588,"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."}}