{"id":"W4298167153","doi":"10.48550/arxiv.1905.12095","title":"On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alberta Innovates; Alberta Innovates - Technology Futures; DeepMind; Alberta Machine Intelligence Institute","keywords":"Mathematics; Countable set; Markov decision process; Action (physics); Duality (order theory); State space; Mathematical optimization; Markov kernel; Discrete mathematics; Markov chain; Applied mathematics; Markov process; Markov model; Variable-order Markov model; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004750078,0.002001646,0.001892737,0.001149007,0.0008096533,0.002974485,0.001808536,0.002332293,0.004348104],"category_scores_gemma":[0.01327294,0.0008327164,0.001555664,0.001454756,0.003450381,0.003854587,0.003128839,0.00341892,0.0003057731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003312325,"about_ca_system_score_gemma":0.002874968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003842867,"about_ca_topic_score_gemma":0.002754653,"domain_scores_codex":[0.9974758,0.001422509,0.00009087542,0.0004157865,0.0003487617,0.0002462291],"domain_scores_gemma":[0.9887866,0.009624019,0.0006480707,0.0001841504,0.0003830217,0.0003742953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005841228,0.00009587286,0.0004685498,0.0002008854,0.00006650439,0.0001540045,0.0001346928,0.3589426,0.0005760296,0.6303299,0.0009398253,0.008032735],"study_design_scores_gemma":[0.00001851644,0.00004163094,0.0001564407,0.00004034894,0.00001496633,0.00002521336,0.00003129674,0.699972,0.00013667,0.298923,0.0006249301,0.00001502078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03997115,0.001777499,0.9414586,0.002113217,0.00007422973,0.00006995751,0.000181903,0.00008628784,0.01426712],"genre_scores_gemma":[0.8162249,0.00308155,0.1615677,0.0007574962,0.0004800693,0.0007956481,0.0004802685,0.0001794606,0.016433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004750078,"threshold_uncertainty_score":0.02512109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1095514681204798,"score_gpt":0.2775900175842334,"score_spread":0.1680385494637536,"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."}}