{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003963928,0.000489725,0.0004881386,0.0003146583,0.0004552075,0.0004170216,0.001682458,0.0003776193,0.00003515217],"category_scores_gemma":[0.00006323248,0.0006161746,0.0004081547,0.000407882,0.00008630912,0.0004983219,0.00250511,0.001002242,0.00006878167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008150958,"about_ca_system_score_gemma":0.0002746061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005972994,"about_ca_topic_score_gemma":0.00001287381,"domain_scores_codex":[0.9971899,0.0002030501,0.0004324716,0.001343474,0.0002181084,0.0006130267],"domain_scores_gemma":[0.9974009,0.0001737874,0.0005803221,0.001258326,0.0003773726,0.0002093256],"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":[0.00002380697,0.00006855232,0.0006606443,0.0001775235,0.0001721632,0.00007502505,0.0004261394,0.9907507,0.0002704658,0.007090853,0.0001027079,0.0001814395],"study_design_scores_gemma":[0.001104168,0.0001494387,0.0004105151,0.0002128751,0.0001137466,0.000006329822,0.000198722,0.9959755,0.0002377348,0.0001245996,0.0008250265,0.0006413441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02301337,0.0000464424,0.9736286,0.00007131085,0.001062145,0.0008852641,0.000002839459,0.0004061324,0.0008838606],"genre_scores_gemma":[0.9690437,0.0001651173,0.02394001,0.0001319677,0.00004581179,0.000007940095,0.0003381539,0.00004082617,0.006286428],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9496886,"threshold_uncertainty_score":0.999629,"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."}}