{"id":"W2950527138","doi":"10.48550/arxiv.math/0506489","title":"Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes","year":2005,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Monotone polygon; Convergence (economics); Mathematical optimization; Algorithm; Markov chain; Operator (biology); Mathematics; Acceleration; Contraction (grammar); Dynamic programming; Computer science; Markov process; Applied 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059775,0.0003064,0.0002550936,0.000203356,0.0002381282,0.0009394393,0.00186871,0.0002618905,0.000009484806],"category_scores_gemma":[0.0006179624,0.0002355561,0.00008834063,0.0004446358,0.00002851022,0.0008294733,0.0006186062,0.0005352158,0.00003879231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552386,"about_ca_system_score_gemma":0.0003418953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002064923,"about_ca_topic_score_gemma":0.00002372726,"domain_scores_codex":[0.9976984,0.0001387459,0.0006102331,0.0006964569,0.0005251632,0.0003310223],"domain_scores_gemma":[0.9979524,0.000475437,0.0002867346,0.0009338812,0.0003130252,0.00003852497],"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":[0.00001209249,0.00005604968,0.01599078,0.0001401117,0.00001611917,0.000003722802,0.002448608,0.9579417,0.00005710642,0.0006869614,0.0008247531,0.02182198],"study_design_scores_gemma":[0.000468502,0.0001154866,0.02666371,0.0002860598,0.0000173438,0.000005194535,0.00005594163,0.9654664,0.001010882,0.0004707658,0.00504161,0.0003980576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1363937,0.0001544514,0.8598895,0.00121577,0.0008330495,0.001175814,0.000002595835,0.00009712602,0.0002379264],"genre_scores_gemma":[0.8548509,0.0001960672,0.1420813,0.001345519,0.0006382907,0.0004334816,0.0001172931,0.00003088002,0.0003063097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7184572,"threshold_uncertainty_score":0.96057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06572374678319638,"score_gpt":0.325058715766949,"score_spread":0.2593349689837526,"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."}}