{"id":"W1601777908","doi":"10.1007/3-540-36755-1_33","title":"Characterizing Markov Decision Processes","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Randomness; Artificial intelligence; Markov chain; Machine learning; Markov process; Measure (data warehouse); Quality (philosophy); Mathematical optimization; Decision problem; Algorithm; Data mining; Mathematics; Statistics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007656733,0.0006507324,0.0005813295,0.001041246,0.0003451233,0.001201194,0.004903324,0.0003685539,0.00009035534],"category_scores_gemma":[0.0004153477,0.0006001848,0.000118085,0.0009896817,0.0004709848,0.001190181,0.002054101,0.001034185,0.0002353315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003417689,"about_ca_system_score_gemma":0.0004769939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003977952,"about_ca_topic_score_gemma":0.000005876737,"domain_scores_codex":[0.9950516,0.00002442955,0.0007163609,0.001701679,0.001642195,0.0008637679],"domain_scores_gemma":[0.9963029,0.0008670126,0.0004799858,0.001744983,0.0003968933,0.0002082157],"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":[0.000004738401,0.00001754459,0.00007109214,0.0001106083,0.00001021507,0.0001248951,0.000677407,0.2291387,0.00007282059,0.003039206,0.00004485008,0.7666879],"study_design_scores_gemma":[0.0002736533,0.0002196087,0.000139396,0.001315135,0.000008770367,0.0001190717,7.973425e-8,0.9669989,0.0008100591,0.0193725,0.009715052,0.001027802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002373716,0.0003243408,0.9859365,0.0004710245,0.002066803,0.0003678667,0.000001508157,0.000285516,0.01052274],"genre_scores_gemma":[0.06023562,0.0003958423,0.9330956,0.002541309,0.0007819463,0.00001289733,0.000007661786,0.00008606448,0.002843064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7656601,"threshold_uncertainty_score":0.9998357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0195282313960036,"score_gpt":0.243811645501996,"score_spread":0.2242834141059924,"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."}}