{"id":"W3193711978","doi":"10.65109/lixm5646","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Curriculum; Cornerstone; Computer science; Diversity (politics); Benchmark (surveying); Variety (cybernetics); Process (computing); Reinforcement learning; Component (thermodynamics); Human–computer interaction; Artificial intelligence; Psychology; Pedagogy; Sociology","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":[0.002816768,0.0005607412,0.00070668,0.0003013989,0.00126305,0.001634579,0.001079775,0.001306977,0.001993975],"category_scores_gemma":[0.01071666,0.0005406723,0.0004368496,0.00022842,0.002173473,0.00401439,0.004058782,0.002523867,0.0005223468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000835851,"about_ca_system_score_gemma":0.001524828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008853459,"about_ca_topic_score_gemma":0.00126545,"domain_scores_codex":[0.99858,0.0005644071,0.00009400581,0.0002680935,0.0003137618,0.0001797017],"domain_scores_gemma":[0.9942624,0.00243437,0.0007240054,0.001066745,0.0005802803,0.0009322648],"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":[0.0002254575,0.0005320587,0.01012636,0.0004952283,0.0001564307,0.0003933097,0.002478995,0.5515873,0.02382733,0.2127986,0.003027601,0.1943513],"study_design_scores_gemma":[0.00009050851,0.000357426,0.002898864,0.0001210765,0.00003963818,0.0003459861,0.0007453705,0.6945859,0.006251798,0.2776529,0.01684498,0.00006535978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1406196,0.0005909593,0.8362103,0.004081617,0.00006448489,0.0002321918,0.00004941814,0.0006993883,0.01745208],"genre_scores_gemma":[0.869589,0.0003241531,0.1270447,0.0003574073,0.0000373844,0.0002150339,0.00005077087,0.00009332797,0.002288266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002816768,"threshold_uncertainty_score":0.01489669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02883001515941496,"score_gpt":0.3124728168870807,"score_spread":0.2836428017276657,"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."}}