{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007550944,0.0006642985,0.0006562005,0.0003723598,0.0002928201,0.0006100365,0.001388641,0.001036041,0.003732745],"category_scores_gemma":[0.002700296,0.000607933,0.0006312576,0.0002401141,0.0005884831,0.0004447541,0.0008528323,0.001067722,0.0005608209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008121212,"about_ca_system_score_gemma":0.00112446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002705743,"about_ca_topic_score_gemma":0.003282384,"domain_scores_codex":[0.9997199,0.00008696117,0.00001296084,0.00005634659,0.0000876179,0.00003614363],"domain_scores_gemma":[0.9990267,0.0005940907,0.0000757075,0.00008182062,0.0001850617,0.00003665524],"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":[0.00003028755,0.00002887213,0.0001262149,0.00004200204,0.00001004179,0.00002556797,0.00002610836,0.9694284,0.00213228,0.006975092,0.0004591508,0.02071595],"study_design_scores_gemma":[0.00000455688,0.00001003784,0.00001544561,0.000002649526,0.000002017565,0.000005531163,0.000001539491,0.9976563,0.0005073812,0.001552702,0.000240372,0.00000135077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007266613,0.00008466026,0.9898139,0.00006377378,0.00002427718,0.0000801483,0.00003539519,0.0004863761,0.002144897],"genre_scores_gemma":[0.6295735,0.000149408,0.3659213,0.00008145149,0.00001840557,0.0004885013,0.0001462665,0.0002240214,0.00339706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003732745,"threshold_uncertainty_score":0.01248723,"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."}}