{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004473194,0.0003296268,0.0002718435,0.000398364,0.0006929338,0.0004019777,0.0004373977,0.0002228555,0.00001717823],"category_scores_gemma":[0.00006991616,0.0003456587,0.00007989896,0.0001140274,0.00006373571,0.002389733,0.0002564431,0.0004593764,0.0001512046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001426357,"about_ca_system_score_gemma":0.0001859233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.491467e-7,"about_ca_topic_score_gemma":5.567946e-7,"domain_scores_codex":[0.9983475,0.000006903826,0.0007667452,0.0002732557,0.0002731589,0.0003324061],"domain_scores_gemma":[0.9981286,0.0001069902,0.0007741724,0.00029445,0.0005620429,0.0001337472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000706816,0.000002982358,0.000001156436,0.0005287993,0.00001479413,1.364288e-7,0.001088514,0.03106699,0.000002221747,0.2142378,0.0001341393,0.7529154],"study_design_scores_gemma":[0.0003740258,0.00006512262,0.000001420804,0.0002216207,0.00001517697,0.000003986632,0.00004708939,0.2806963,0.00002981243,0.001666066,0.7165865,0.0002929461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[1.223499e-7,0.000468517,0.5808268,0.00002210618,0.0001012405,0.0005405451,9.394682e-7,0.00017989,0.4178598],"genre_scores_gemma":[0.003264608,0.001098951,0.2471158,0.0008798228,0.0002839048,0.000385304,0.0005117878,0.00008176514,0.746378],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7526225,"threshold_uncertainty_score":0.9998996,"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."}}