{"id":"W4313061161","doi":"10.1007/978-3-031-19679-9_63","title":"Reinforcement Learning for Exploring Pedagogical Strategies in Virtual Reality Training","year":2022,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"TUTOR; Reinforcement learning; Computer science; Virtual reality; Reinforcement; Human–computer interaction; Training (meteorology); Multimedia; Artificial intelligence; Psychology","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":[0.002621945,0.000256856,0.0003281405,0.001154136,0.0008124138,0.0008821107,0.003214277,0.00009399759,0.00002030657],"category_scores_gemma":[0.0001343606,0.0002837469,0.00006315485,0.0004792919,0.0004678682,0.01126159,0.003245948,0.0009493324,0.000008067975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003916015,"about_ca_system_score_gemma":0.0005951292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002023278,"about_ca_topic_score_gemma":0.000008991491,"domain_scores_codex":[0.9974515,0.00006485577,0.001048929,0.0003630795,0.0006793498,0.0003923113],"domain_scores_gemma":[0.9973245,0.0005236203,0.0004686867,0.001384006,0.0002060229,0.00009319527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002306909,0.000002861319,0.00000708862,0.00001270123,0.000001986503,2.290891e-7,0.007750892,0.4714378,4.661735e-7,0.4852641,0.000008429138,0.03551115],"study_design_scores_gemma":[0.0003315516,0.0001828239,0.0001453863,0.0001057752,0.00000253466,0.000006570975,0.0008118945,0.8412448,9.235936e-7,0.002607661,0.1542863,0.0002737069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003759839,0.00004971129,0.8763994,0.0004823856,0.0002703469,0.0004935682,0.000001524133,0.00009883327,0.1221666],"genre_scores_gemma":[0.795773,0.006289433,0.1894732,0.001110094,0.0001354643,0.0008656256,0.0003903971,0.00004739622,0.005915387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7957354,"threshold_uncertainty_score":0.9999615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3056666438607475,"score_gpt":0.3725653755714306,"score_spread":0.06689873171068311,"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."}}