{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001356152,0.0008515709,0.0003761617,0.0004003274,0.0007122393,0.001900382,0.001753025,0.001635472,0.02175489],"category_scores_gemma":[0.004926422,0.0004773067,0.0005971236,0.0002442302,0.002445651,0.002947508,0.003830878,0.002385539,0.005313823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007248333,"about_ca_system_score_gemma":0.001166605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002982959,"about_ca_topic_score_gemma":0.005900876,"domain_scores_codex":[0.9994915,0.0001609591,0.000026576,0.0001220831,0.0001383661,0.00006060579],"domain_scores_gemma":[0.9990404,0.0003673606,0.00005464874,0.000321898,0.00009233745,0.0001232715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00051874,0.0003211097,0.001755926,0.0006763419,0.0001070772,0.0004833514,0.001788886,0.1724668,0.0174808,0.3440196,0.1123844,0.3479968],"study_design_scores_gemma":[0.0001293942,0.0001878566,0.0007019712,0.000299482,0.00003182068,0.0003033124,0.0001866343,0.4225765,0.01686666,0.1795608,0.3790522,0.0001034144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007485554,0.0002708191,0.9212444,0.002227392,0.0003321907,0.0001892392,0.0004312871,0.02825341,0.03956568],"genre_scores_gemma":[0.1750396,0.0004682051,0.7804693,0.001409623,0.0001018879,0.0005023501,0.001034099,0.007107737,0.0338672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02175489,"threshold_uncertainty_score":0.07277733,"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."}}