{"id":"W4403793598","doi":"10.1007/978-3-031-75872-0_10","title":"Model-Driven Design and Generation of Training Simulators for Reinforcement Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina; University of Toronto; York University","funders":"","keywords":"Computer science; Reinforcement learning; Training (meteorology); Artificial intelligence; Human–computer interaction; Simulation","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"],"consensus_categories":[],"category_scores_codex":[0.001005257,0.0003895977,0.0004478777,0.0006741695,0.0002109395,0.0003929912,0.001081648,0.0002315288,0.000002759854],"category_scores_gemma":[0.0001146303,0.0003704165,0.0001012795,0.0002818821,0.0003142041,0.0004344349,0.0006660909,0.0005461898,0.000003237004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839572,"about_ca_system_score_gemma":0.0004178371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001807554,"about_ca_topic_score_gemma":0.000001656159,"domain_scores_codex":[0.9972311,0.00002129897,0.0006045036,0.0009884302,0.0007028051,0.0004518252],"domain_scores_gemma":[0.9983019,0.0005099087,0.0003310219,0.0005375437,0.0002157517,0.0001039154],"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":[0.000003300128,0.000001906615,0.000002992345,0.00007068712,0.00001467245,0.000003505395,0.002123674,0.9184095,0.0003579661,0.03375867,0.000003912557,0.04524927],"study_design_scores_gemma":[0.0001989977,0.0003477049,6.000352e-7,0.0003277922,0.00001741556,0.000007476012,3.730937e-7,0.9769475,0.000916998,0.02068003,0.000196705,0.0003583541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000375762,0.0001671929,0.9977151,0.000129453,0.000651592,0.0006841128,6.776695e-7,0.0001103242,0.0005039929],"genre_scores_gemma":[0.3517327,0.00003169772,0.6470833,0.0001342353,0.0001533565,0.00001149652,0.000005485345,0.00003088056,0.0008168478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3516951,"threshold_uncertainty_score":0.9998748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07555659613702641,"score_gpt":0.2797578082053195,"score_spread":0.2042012120682931,"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."}}