{"id":"W2081102656","doi":"10.1007/s00186-013-0432-y","title":"Accelerated modified policy iteration algorithms for Markov decision processes","year":2013,"lang":"en","type":"article","venue":"Mathematical Methods of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Convergence (economics); Markov chain; Operator (biology); Mathematical optimization; Computer science; Markov process; Algorithm; Markov model; Partially observable Markov decision process; Mathematics; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003854922,0.0001494421,0.0002891806,0.0005872145,0.0004163149,0.0009645427,0.0009913023,0.0001187324,0.0001485173],"category_scores_gemma":[0.0160727,0.0001181808,0.00006259329,0.001748621,0.0001383956,0.001083867,0.0003706024,0.0002575664,0.00009018952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008210746,"about_ca_system_score_gemma":0.0004678654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000436806,"about_ca_topic_score_gemma":0.00000144916,"domain_scores_codex":[0.9971259,0.0005769469,0.0006778726,0.0003755067,0.000783888,0.0004598962],"domain_scores_gemma":[0.9920178,0.004148528,0.00005426645,0.0007325461,0.00289739,0.0001494671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001723216,0.0003090999,0.000005713352,0.0005840243,0.00004919787,6.835875e-7,0.001768959,0.25402,0.01594427,0.4822529,0.001152939,0.243895],"study_design_scores_gemma":[0.0002703775,0.000197871,0.00003067011,0.00007225565,0.000003067294,0.000003448513,0.00005790544,0.9205285,0.01493796,0.06361915,0.0001664432,0.0001123113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001479163,0.00002574859,0.9927419,0.001796239,0.00005277491,0.00164682,0.000002306979,0.0000715109,0.002183577],"genre_scores_gemma":[0.03762729,0.00001501585,0.959797,0.00005656508,0.00007008629,0.0007448823,0.000008815873,0.00001863481,0.001661729],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6665086,"threshold_uncertainty_score":0.9922153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2714919902690478,"score_gpt":0.5351392337457531,"score_spread":0.2636472434767053,"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."}}