{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003669835,0.001091723,0.001678396,0.0006342681,0.0004953208,0.001364725,0.002247252,0.002165484,0.004323912],"category_scores_gemma":[0.01626253,0.0006654125,0.000848236,0.0006272251,0.002181003,0.00280658,0.002266575,0.00269569,0.0008592313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001065626,"about_ca_system_score_gemma":0.001958293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001563452,"about_ca_topic_score_gemma":0.001383555,"domain_scores_codex":[0.9977587,0.0007772394,0.0001021704,0.0003815333,0.0008363911,0.0001439383],"domain_scores_gemma":[0.9937909,0.003937752,0.0003856168,0.0007976196,0.0009061482,0.0001818905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001090265,0.0000890744,0.0004330273,0.0001107791,0.00005973839,0.00008219263,0.000147784,0.8188213,0.001802066,0.1340393,0.001246864,0.04305878],"study_design_scores_gemma":[0.00001043652,0.00003010967,0.00001824394,0.000007143502,0.000003982234,0.00002001306,0.000004942556,0.9838551,0.0004216123,0.01509764,0.0005265219,0.000004222382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005081657,0.00008733581,0.9914243,0.0001209609,0.00003769861,0.00003818819,0.0000183371,0.0001546293,0.003036822],"genre_scores_gemma":[0.4638347,0.0003038725,0.5257694,0.000328819,0.0001312216,0.0005312125,0.0001412151,0.0001946108,0.00876492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004323912,"threshold_uncertainty_score":0.01940817,"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."}}