{"id":"W2103568863","doi":"10.48550/arxiv.1407.0449","title":"Classification-based Approximate Policy Iteration: Experiments and Extended Discussions","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exploit; Estimator; Computer science; Reinforcement learning; Bellman equation; Classifier (UML); Nonparametric statistics; Function (biology); Temporal difference learning; Mathematical optimization; Machine learning; Artificial intelligence; Algorithm; Mathematics; Econometrics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007213106,0.001380252,0.001930215,0.000678547,0.0009366816,0.001349968,0.002008606,0.002631445,0.006044226],"category_scores_gemma":[0.04318187,0.0004448661,0.0007785911,0.001330814,0.001337798,0.002902755,0.001907738,0.003447418,0.001090259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001468035,"about_ca_system_score_gemma":0.002067816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01154662,"about_ca_topic_score_gemma":0.00682602,"domain_scores_codex":[0.9962327,0.001774603,0.000293326,0.0005140254,0.0007849573,0.0004003154],"domain_scores_gemma":[0.9655124,0.0257557,0.001311165,0.004150382,0.002558936,0.0007113651],"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":[0.002484642,0.003031871,0.006157955,0.001274161,0.0002666918,0.0001753882,0.0003215718,0.809489,0.002835553,0.01770642,0.01764091,0.1386159],"study_design_scores_gemma":[0.0002465585,0.0003946638,0.0008140261,0.00006087742,0.00003472335,0.00004300128,0.00009256813,0.9799549,0.002511806,0.01371354,0.002106828,0.00002655589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5574746,0.01224345,0.3776752,0.005360584,0.001081616,0.001358033,0.002219225,0.00455002,0.03803715],"genre_scores_gemma":[0.8947501,0.001001046,0.0974792,0.0005470537,0.0001111898,0.0006627474,0.001504439,0.000301176,0.003643071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01154662,"threshold_uncertainty_score":0.03814697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08066957996727817,"score_gpt":0.2334431306103826,"score_spread":0.1527735506431045,"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."}}