{"id":"W7124247225","doi":"10.65109/vzsi9543","title":"Hiking up that HILL with Cogment-Verse: Train & Operate Multi-agent Systems Learning from Humans","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Network for Business Sustainability; Institut national de psychiatrie légale Philippe-Pinel","funders":"","keywords":"Variety (cybernetics); Reinforcement learning; Generalization; Context (archaeology); Formalism (music); Applications of artificial intelligence","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","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002397858,0.001014537,0.000974238,0.0005380178,0.001589714,0.003370452,0.002214497,0.0003545147,0.0009620934],"category_scores_gemma":[0.0001857362,0.0008986808,0.000256745,0.001684758,0.0002741224,0.001429586,0.001368624,0.001482212,0.004668406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005288805,"about_ca_system_score_gemma":0.0003131385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015018,"about_ca_topic_score_gemma":0.0001633586,"domain_scores_codex":[0.9915737,0.001169954,0.001269274,0.001993096,0.002062128,0.001931832],"domain_scores_gemma":[0.9960607,0.0005879331,0.0007908814,0.00167898,0.0003140326,0.0005674335],"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":[0.000028604,0.00005133459,0.006879425,0.000126118,0.0003982585,0.0001508889,0.02415583,0.963138,0.0008252593,0.001267859,0.001414782,0.001563667],"study_design_scores_gemma":[0.002602688,0.0003222971,0.001973064,0.0008670073,0.0001068299,0.00001492344,0.009011345,0.9501884,0.0001941471,0.000002714763,0.03353098,0.001185597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03314126,0.0003013417,0.9545748,0.0005050352,0.005172735,0.001346259,0.00001071327,0.001393334,0.003554567],"genre_scores_gemma":[0.8242202,0.0003799673,0.009934323,0.000262,0.0002988325,0.00006949723,0.0001639864,0.0001426335,0.1645286],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9446405,"threshold_uncertainty_score":0.9999512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.125970409349111,"score_gpt":0.290253081006849,"score_spread":0.164282671657738,"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."}}