{"id":"W1591992921","doi":"10.48550/arxiv.1207.4114","title":"Metrics for Finite Markov Decision Processes","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Reinforcement learning; Metric (unit); Markov process; Computer science; Markov kernel; Markov chain; Aggregate (composite); Bellman equation; Mathematical optimization; Q-learning; Similarity (geometry); Variable-order Markov model; Artificial intelligence; Markov model; Machine learning; Mathematics","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":[0.005254249,0.001948799,0.001426415,0.003596262,0.001130964,0.003519558,0.00174653,0.002040862,0.004080254],"category_scores_gemma":[0.03643912,0.0005769226,0.001212018,0.002684942,0.002684503,0.007987447,0.003365822,0.003338325,0.0007347395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003477024,"about_ca_system_score_gemma":0.001508225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001969097,"about_ca_topic_score_gemma":0.001255649,"domain_scores_codex":[0.9924541,0.002834918,0.0008924942,0.001228252,0.002197628,0.0003926003],"domain_scores_gemma":[0.974121,0.01680393,0.003259301,0.001725711,0.002693051,0.001397081],"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":[0.00006225424,0.00004498997,0.001279979,0.0002358909,0.00008051059,0.0001008836,0.0002202405,0.1041972,0.0009841493,0.855566,0.002310076,0.03491783],"study_design_scores_gemma":[0.000008714562,0.0000761536,0.0003341628,0.0000564264,0.00001753563,0.00007910645,0.00003375939,0.2325019,0.0004344255,0.7610672,0.005363937,0.0000267462],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01623436,0.003444109,0.9718736,0.000770467,0.0001696732,0.0001253394,0.0005367389,0.0002824379,0.00656334],"genre_scores_gemma":[0.5679325,0.003666876,0.419554,0.0005157906,0.0005000349,0.000928324,0.001864538,0.0002969683,0.004740864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005254249,"threshold_uncertainty_score":0.02778751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07973034372712487,"score_gpt":0.2043299711430501,"score_spread":0.1245996274159252,"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."}}