{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001837513,0.0002963694,0.0002523024,0.0003492727,0.000292699,0.0003406569,0.001167028,0.0002142085,0.00001751182],"category_scores_gemma":[0.00006470938,0.0002963532,0.0001034369,0.0003912542,0.0001347023,0.0003175031,0.00113583,0.0003734852,0.00004011893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001937821,"about_ca_system_score_gemma":0.0002330252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002888381,"about_ca_topic_score_gemma":0.000001427995,"domain_scores_codex":[0.9982202,0.0001767429,0.0002349211,0.0009313857,0.0001340307,0.0003026931],"domain_scores_gemma":[0.9979127,0.00009284835,0.0003184399,0.001362561,0.0001158475,0.0001975701],"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":[0.000006556977,0.00003968825,0.0006990739,0.00004476217,0.00002420597,0.00001086188,0.0002008504,0.7614193,0.00007173058,0.2371168,0.0001001586,0.0002659817],"study_design_scores_gemma":[0.0004044423,0.00004207495,0.002140626,0.00007688242,0.00002120035,0.000001165496,0.00003862477,0.9920532,0.000107816,0.004333441,0.000450411,0.0003300945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009655893,0.00001404827,0.9860879,0.0006279668,0.0002780584,0.000313128,0.000003491848,0.0002549824,0.002764537],"genre_scores_gemma":[0.9887046,0.00002867334,0.008698927,0.0002157733,0.00008669002,0.000003907089,0.00004329838,0.00001781702,0.002200311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790487,"threshold_uncertainty_score":0.9999489,"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."}}