{"id":"W2964363500","doi":"10.11159/cist19.118","title":"LongiControl: A New Reinforcement Learning Environment","year":2019,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Computer science; Human–computer interaction; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004256504,0.0001722962,0.0002403089,0.0001926448,0.0001467284,0.000412618,0.0008184094,0.00003027064,0.00000114054],"category_scores_gemma":[0.00003118641,0.000122587,0.00003964332,0.0006048366,0.00007123755,0.000328799,0.0004533667,0.0002678287,0.00000379253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005550832,"about_ca_system_score_gemma":0.00003318386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000884795,"about_ca_topic_score_gemma":5.198977e-8,"domain_scores_codex":[0.9983731,0.000005457418,0.0002707069,0.0004128418,0.0005711672,0.000366728],"domain_scores_gemma":[0.9993533,0.00008205017,0.0001729305,0.0001791548,0.00005672964,0.0001558049],"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":[0.000005058394,0.000006670381,0.002627134,0.00005009853,0.00001331059,3.180771e-7,0.00009397019,0.8772922,0.001852443,0.1153946,0.000113143,0.002551098],"study_design_scores_gemma":[0.0002976804,0.0002541242,0.00211731,0.0001589438,0.000004637033,0.00001462638,0.000002708312,0.9932398,0.0006703192,0.00001581649,0.003071857,0.0001521425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2704549,0.001101821,0.7174401,0.001060836,0.004497122,0.00163385,2.041724e-7,0.0004117812,0.003399405],"genre_scores_gemma":[0.9935502,0.0000330932,0.001769836,0.00005158036,0.00007286551,0.000006207619,4.167421e-8,0.00000757722,0.004508566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7230954,"threshold_uncertainty_score":0.4998954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005112510692350032,"score_gpt":0.1814282125382291,"score_spread":0.1763157018458791,"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."}}