{"id":"W2105336508","doi":"","title":"A Convergent Form of Approximate Policy Iteration","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Lipschitz continuity; Convergence (economics); Operator (biology); Action (physics); Mathematics; Constant (computer programming); Mathematical optimization; Function (biology); Applied mathematics; Bellman equation; State (computer science); Computer science; Algorithm; Mathematical analysis","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006613783,0.00006626507,0.0001493824,0.0003593595,0.00005781622,0.00006829479,0.0003563267,0.00003340969,0.00666677],"category_scores_gemma":[0.001415993,0.000043076,0.0000612132,0.0009041767,0.00007770101,0.0004007349,0.00009898443,0.00005799532,0.0007521902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003970194,"about_ca_system_score_gemma":0.0000222254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002982966,"about_ca_topic_score_gemma":0.00001089892,"domain_scores_codex":[0.9979058,0.00004428199,0.0004114911,0.0002189794,0.001210141,0.0002093006],"domain_scores_gemma":[0.9988318,0.0002754209,0.0001009458,0.0003808252,0.0003273062,0.00008367298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005902591,0.0004678283,0.002958045,0.00002556098,0.00003549022,0.00001444713,0.005577375,0.001056421,0.005800228,0.04902202,0.05517959,0.879804],"study_design_scores_gemma":[0.0009440474,0.0002106379,0.001797771,0.000008126662,0.00000247226,0.00001476957,0.0005771981,0.7455637,0.03780047,0.1693975,0.04347346,0.0002098362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05597288,0.0001637324,0.8673233,0.00418224,0.0002623348,0.0005702148,0.00002797438,0.00008142239,0.07141583],"genre_scores_gemma":[0.9647919,0.00003522326,0.005776619,0.0001125747,0.00008588855,0.00001139579,0.000001443627,0.000006235561,0.0291787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.908819,"threshold_uncertainty_score":0.9942413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833628301305216,"score_gpt":0.4441139764675269,"score_spread":0.2607511463370052,"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."}}