{"id":"W1595080983","doi":"10.1109/acc.2015.7171887","title":"Finite state approximations of Markov decision processes with general state and action spaces","year":2015,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Markov decision process; Action (physics); Finite state; Markov process; Complement (music); State space; Mathematical optimization; Markov chain; Applied mathematics; Mathematics; State (computer science); Partially observable Markov decision process; Markov model; Stochastic process; Markov kernel; Approximations of π; Computer science; Variable-order Markov model; 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":[0.002996358,0.0009081318,0.001445758,0.0007057815,0.0004554502,0.001883952,0.001743429,0.001313907,0.001808957],"category_scores_gemma":[0.01525429,0.0007390389,0.001221503,0.0007917273,0.002272935,0.002395427,0.001427789,0.002803213,0.0002421047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002841606,"about_ca_system_score_gemma":0.00177603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056045,"about_ca_topic_score_gemma":0.007207283,"domain_scores_codex":[0.9981297,0.0008262715,0.0001122516,0.0003137872,0.0004513062,0.0001668066],"domain_scores_gemma":[0.9893129,0.00836774,0.001040693,0.0006216416,0.0004120311,0.0002449773],"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":[0.00003149267,0.00001508001,0.000235689,0.00002916604,0.00001777524,0.00003739137,0.00004464406,0.9227804,0.0001690025,0.07403399,0.00009205625,0.00251332],"study_design_scores_gemma":[0.000003722308,0.000006016076,0.00003398747,0.000005679438,0.000002423081,0.000004613019,0.000004281663,0.971316,0.00006047088,0.02844179,0.0001178869,0.000003054555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04361826,0.0005057452,0.9526401,0.0002955082,0.00004407212,0.00002843909,0.0001059497,0.0001264473,0.002635517],"genre_scores_gemma":[0.8809926,0.0006758776,0.1144651,0.00009941462,0.00006000196,0.0001599709,0.0003084342,0.00005617055,0.003182526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01056045,"threshold_uncertainty_score":0.02099794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03449294913191672,"score_gpt":0.2734357435885215,"score_spread":0.2389427944566048,"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."}}