{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004035531,0.0005596053,0.0003207839,0.0001900817,0.0001979598,0.0008651081,0.0008014166,0.000614049,0.008315252],"category_scores_gemma":[0.001616272,0.0001439518,0.0002356597,0.0002581034,0.0005795261,0.0008213506,0.0006137219,0.0008746343,0.0008295959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006172662,"about_ca_system_score_gemma":0.0003847378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001202583,"about_ca_topic_score_gemma":0.00172384,"domain_scores_codex":[0.9997833,0.0001130217,0.000006843487,0.0000280694,0.00005603779,0.00001277441],"domain_scores_gemma":[0.999598,0.0003223991,0.00001685821,0.00002041375,0.00002788638,0.00001449981],"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":[0.0001388695,0.0001259782,0.0003109688,0.0004063238,0.00003786095,0.0001091584,0.0006029034,0.1213007,0.008249153,0.2217031,0.006845842,0.6401691],"study_design_scores_gemma":[0.00008166982,0.0003204906,0.001018499,0.0003876125,0.00004356102,0.0003320406,0.000423274,0.6478329,0.008102952,0.2708279,0.07056879,0.00006024753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01425567,0.005768724,0.9177073,0.0004899161,0.0001803711,0.00009426846,0.00005632529,0.0006251395,0.06082229],"genre_scores_gemma":[0.4677099,0.004543985,0.4766485,0.0001694723,0.0001028837,0.0004278225,0.0001124701,0.0001501503,0.05013482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008315252,"threshold_uncertainty_score":0.02781731,"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."}}