{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001202903,0.000706442,0.0006775564,0.0004805028,0.0005253339,0.0015929,0.003552134,0.001252083,0.01927641],"category_scores_gemma":[0.003154702,0.0004350295,0.0006664059,0.000290139,0.001012469,0.001999848,0.003847409,0.003064471,0.004864049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006628922,"about_ca_system_score_gemma":0.001301423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001068934,"about_ca_topic_score_gemma":0.001862397,"domain_scores_codex":[0.9992181,0.000242842,0.00003817082,0.000159049,0.0002721466,0.00006970778],"domain_scores_gemma":[0.9990833,0.0004268104,0.00007694677,0.0001315956,0.0000946253,0.0001866439],"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":[0.001298766,0.0008816097,0.00162247,0.0004485972,0.0001132653,0.0007388533,0.0004398656,0.2769451,0.01351657,0.1941434,0.06977466,0.440077],"study_design_scores_gemma":[0.0002373557,0.0001993653,0.0001402532,0.00005069998,0.00002104222,0.0001945235,0.00002411946,0.8056546,0.005186643,0.06757115,0.1206706,0.00004962064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003549369,0.0003099563,0.9644152,0.0006141444,0.0002589234,0.0001338983,0.0002993255,0.0172508,0.01316837],"genre_scores_gemma":[0.1680635,0.0005223612,0.7980285,0.001456407,0.0002212439,0.0009306422,0.001015824,0.00285098,0.02691058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01927641,"threshold_uncertainty_score":0.06448603,"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."}}