{"id":"W161119602","doi":"10.1007/978-1-84628-758-9_9","title":"Reinforcement Agents for E-Learning Applications","year":2007,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Process (computing); Set (abstract data type); Reinforcement; Error-driven learning; Human–computer interaction; Artificial intelligence; Punishment (psychology); Engineering","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":[0.0001721789,0.0006766813,0.0004420461,0.0002709249,0.0002277374,0.0009668243,0.0007635214,0.0009947413,0.01827865],"category_scores_gemma":[0.0005157613,0.0002364195,0.0002306492,0.0005560966,0.0003846401,0.001173883,0.0006434878,0.001204465,0.00504337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004045112,"about_ca_system_score_gemma":0.0003744312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006284916,"about_ca_topic_score_gemma":0.0008662859,"domain_scores_codex":[0.9998691,0.00002567596,0.000006557372,0.00001757051,0.00007210947,0.000008964019],"domain_scores_gemma":[0.9998642,0.00006639013,0.000006716313,0.00002162886,0.00003148619,0.000009620639],"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":[0.00003138878,0.000101409,0.00008661961,0.000389055,0.00002134139,0.0001021438,0.00008169265,0.03091566,0.004240247,0.2186362,0.05182094,0.6935732],"study_design_scores_gemma":[0.000031432,0.00005933728,0.000199433,0.000229353,0.00001990572,0.0003238379,0.00005167357,0.1255945,0.005336369,0.241939,0.626192,0.00002313437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003860416,0.02166638,0.7607265,0.001281051,0.001074089,0.0001242318,0.0001704553,0.002327637,0.2087692],"genre_scores_gemma":[0.1076311,0.02279179,0.4696947,0.0005714414,0.0005991842,0.0004029942,0.000488434,0.0005567674,0.3972636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01827865,"threshold_uncertainty_score":0.06114823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02962264394858856,"score_gpt":0.3018086292081156,"score_spread":0.2721859852595271,"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."}}