{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001927588,0.00008466821,0.00009687436,0.00009641088,0.00004675177,0.0001569307,0.0001893569,0.00001622735,0.000004885247],"category_scores_gemma":[0.0001414625,0.00006024035,0.000007618904,0.000330645,0.0000445402,0.0007295236,0.0001088213,0.00005225764,0.000007546424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001652807,"about_ca_system_score_gemma":0.0001570049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003238026,"about_ca_topic_score_gemma":0.0000484882,"domain_scores_codex":[0.9992052,0.00002328396,0.0001623803,0.0001700678,0.0003104179,0.00012867],"domain_scores_gemma":[0.9991999,0.0001214684,0.0001319083,0.0002093024,0.0002609503,0.00007653075],"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":[0.00002381365,0.0000159085,0.002153315,0.00005906085,0.00001223404,0.000002233924,0.001245275,0.9830353,0.000048118,0.0006447783,0.0003291722,0.01243078],"study_design_scores_gemma":[0.000482694,0.0003151757,0.00144002,0.00004389471,0.000005206308,0.00001134095,0.0001159061,0.9934305,0.002189563,0.001168572,0.000663854,0.0001332636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1163972,0.00001718877,0.88182,0.0001060122,0.00004651691,0.0001102844,6.941096e-7,0.000047465,0.001454649],"genre_scores_gemma":[0.4767194,0.00007177121,0.5192798,0.0000395784,0.000008967285,0.000006347954,0.000002509393,0.000006706175,0.003864931],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3625402,"threshold_uncertainty_score":0.245653,"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."}}