{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002341636,0.001086256,0.001743111,0.0007912834,0.0007434209,0.001815621,0.001734377,0.001311677,0.004963823],"category_scores_gemma":[0.007912301,0.0009381236,0.0008292482,0.001422788,0.00249824,0.003185132,0.001883382,0.00256826,0.0003238836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002679796,"about_ca_system_score_gemma":0.001921645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006205364,"about_ca_topic_score_gemma":0.005593534,"domain_scores_codex":[0.9990152,0.0004473647,0.00005579037,0.0001593039,0.0001941906,0.0001280753],"domain_scores_gemma":[0.995401,0.003767826,0.0002704766,0.0001742635,0.0002059236,0.0001806231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007655281,0.00004560752,0.0002618994,0.0001016483,0.00003379771,0.00004513175,0.0001290167,0.5483039,0.0005276985,0.432121,0.001241412,0.01711231],"study_design_scores_gemma":[0.0000141243,0.00001718412,0.00007816427,0.00002233095,0.000005439295,0.000008550474,0.00001300987,0.6248916,0.0001293514,0.3743063,0.0005057479,0.000008311386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04324519,0.002021669,0.939275,0.0007654661,0.0001371693,0.00006486428,0.0001863135,0.0001773714,0.01412696],"genre_scores_gemma":[0.7577541,0.003773529,0.2281005,0.0002995328,0.0002168354,0.0003104109,0.0004615669,0.0002183732,0.008865212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006205364,"threshold_uncertainty_score":0.01944339,"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."}}