{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003599529,0.0001992288,0.0002645581,0.0001161771,0.0003814997,0.000672661,0.0006784498,0.00007787741,0.0001780847],"category_scores_gemma":[0.0004822423,0.0001871807,0.0001470399,0.0004943792,0.00005382055,0.0005214537,0.000576369,0.0002564301,0.0001956022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221375,"about_ca_system_score_gemma":0.0001230418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00038979,"about_ca_topic_score_gemma":0.00003054602,"domain_scores_codex":[0.9978324,0.0001332959,0.0004016694,0.000586218,0.0004967591,0.0005496278],"domain_scores_gemma":[0.9981844,0.0004854134,0.00009974367,0.0005793068,0.000458786,0.0001923113],"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":[0.000003809585,0.0001319446,0.0251326,0.0003294206,0.00009124534,0.0001590394,0.0009407702,0.5179899,0.0002875923,0.4294734,0.02290012,0.002560133],"study_design_scores_gemma":[0.0003505335,0.00007542763,0.0005574963,0.00005946629,0.00002073464,0.00001108604,0.0008296503,0.963612,0.0009994443,0.00004748226,0.03316936,0.0002672742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001066857,0.00005466686,0.9791616,0.001154929,0.001257292,0.0002552086,0.000001639273,0.0004366077,0.01661118],"genre_scores_gemma":[0.8648701,0.00004202433,0.08701781,0.0005421155,0.0002187003,0.0000568722,0.00001517321,0.00002692505,0.04721024],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8921438,"threshold_uncertainty_score":0.7633005,"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."}}