{"id":"W187740018","doi":"10.1007/978-1-4757-3561-1_5","title":"On Optimal Policies of Multichain Finite State Compact Action Markov Decision Processes","year":2002,"lang":"en","type":"book-chapter","venue":"Advances in computational management science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Markov decision process; Markov process; Action (physics); Set (abstract data type); Mathematical optimization; Markov chain; State (computer science); Finite set; Markov model; Computer science; Mathematics; Mathematical economics; Applied mathematics; Algorithm","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":[0.0006396351,0.0003808241,0.0003669057,0.001442972,0.0002210161,0.000212979,0.001872589,0.00006139148,0.00003800257],"category_scores_gemma":[0.0002353924,0.0003776426,0.00007087229,0.0008191494,0.0005702518,0.001623032,0.0005085522,0.0002972574,0.00007077344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003050675,"about_ca_system_score_gemma":0.0001061941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004133645,"about_ca_topic_score_gemma":0.000004493701,"domain_scores_codex":[0.9958037,0.00002402496,0.0007584537,0.0008574476,0.002127324,0.000429047],"domain_scores_gemma":[0.9969217,0.001347059,0.000761773,0.0005524806,0.000324579,0.00009246554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001857348,0.00003148464,0.00002752755,0.0001530255,0.00001038567,0.00002307063,0.0001301178,0.7719178,4.277587e-7,0.1997489,0.00005929158,0.02787941],"study_design_scores_gemma":[0.000434105,0.000225848,0.0005160107,0.0009022484,0.000008826568,0.000005453226,0.00001563082,0.9126065,0.0000166976,0.0784964,0.006365515,0.0004067622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001121707,0.0002028408,0.8734115,0.000115255,0.0004538416,0.000453856,0.000007292273,0.00007930381,0.1251639],"genre_scores_gemma":[0.4230037,0.004020106,0.4941093,0.0006000182,0.00007725186,0.00002735156,0.00003906348,0.00007536538,0.07804781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4228915,"threshold_uncertainty_score":0.9998676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02400273753884332,"score_gpt":0.3064423695527335,"score_spread":0.2824396320138902,"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."}}