{"id":"W2012045703","doi":"10.1287/moor.27.3.545.316","title":"Achieving Target State-Action Frequencies in Multichain Average-Reward Markov Decision Processes","year":2002,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Stochastic game; Construct (python library); Mathematics; Action (physics); Mathematical optimization; Markov process; State space; Markov chain; State (computer science); Space (punctuation); Decision problem; Mathematical economics; Computer science; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.001928058,0.0001330951,0.0002177475,0.000645137,0.0002917592,0.0003956236,0.000906223,0.00006534365,0.0001291783],"category_scores_gemma":[0.003614251,0.0001209239,0.00003459455,0.001388552,0.0001123475,0.0008903032,0.0003326246,0.0003936491,0.0001158649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001454083,"about_ca_system_score_gemma":0.0001240119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007101005,"about_ca_topic_score_gemma":0.000106582,"domain_scores_codex":[0.9974393,0.0001824045,0.0005990625,0.0002855338,0.00109402,0.0003996551],"domain_scores_gemma":[0.9975976,0.0009225907,0.00006317652,0.0006382023,0.0007052718,0.00007320711],"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":[0.000002299087,0.000181441,0.0003476327,0.0002714632,0.000008802008,0.000007071317,0.007752599,0.9827173,0.002595667,0.003591959,0.0001751588,0.002348582],"study_design_scores_gemma":[0.0002189501,0.000102604,0.0001678905,0.0002014863,0.000001065053,0.00000411408,0.0003519153,0.9946882,0.00320064,0.0007802323,0.0001619832,0.0001209135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1057416,0.0001097305,0.8913088,0.0003155125,0.00006227638,0.0004642529,0.000002124935,0.00005166388,0.001944024],"genre_scores_gemma":[0.6136735,0.000144814,0.3847877,0.000008554014,0.00001128687,0.00004209444,0.000002323631,0.00001194001,0.001317732],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5079319,"threshold_uncertainty_score":0.4931132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1287887858977092,"score_gpt":0.3733220047753127,"score_spread":0.2445332188776035,"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."}}