{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003098907,0.0007964407,0.001164758,0.0006363628,0.0007850661,0.001054125,0.001012705,0.001223208,0.001341724],"category_scores_gemma":[0.007434989,0.0005727917,0.0005546281,0.0007543579,0.001988756,0.002376484,0.001487708,0.001278222,0.000191018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001710534,"about_ca_system_score_gemma":0.001630429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004738723,"about_ca_topic_score_gemma":0.004171516,"domain_scores_codex":[0.9985216,0.0005838642,0.00007874495,0.0003773996,0.0002367002,0.0002015488],"domain_scores_gemma":[0.995923,0.002895493,0.0006064384,0.0001594072,0.0001864364,0.0002291683],"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":[0.0001010164,0.0000684611,0.0006927276,0.00004674825,0.00002471932,0.00007264789,0.0001141221,0.9197983,0.0008741887,0.06785767,0.0001314089,0.01021809],"study_design_scores_gemma":[0.00002620387,0.00004685935,0.0001565068,0.000008673303,0.000006543357,0.00001265536,0.00001698696,0.9389081,0.0005475379,0.06009363,0.0001673463,0.000008917876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2087307,0.000174893,0.7884183,0.000301561,0.00001414167,0.00006841552,0.00007218122,0.0001841639,0.002035711],"genre_scores_gemma":[0.8982053,0.0001504529,0.1002423,0.00006252663,0.00001387555,0.0001372552,0.00009023435,0.00003925787,0.001058656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004738723,"threshold_uncertainty_score":0.01638877,"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."}}