{"id":"W4399486984","doi":"10.1109/tnnls.2024.3373749","title":"Off-Policy Prediction Learning: An Empirical Study of Online Algorithms","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"DeepMind; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Machine learning; Artificial intelligence; Empirical research; Algorithm; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00203285,0.0002793233,0.0005124779,0.000870546,0.0006397011,0.0005285898,0.0003498692,0.0001861916,0.00004339329],"category_scores_gemma":[0.0001765909,0.0002085556,0.0001311642,0.001993496,0.0001479665,0.0005804799,0.000008326308,0.002054907,0.00001345268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007729546,"about_ca_system_score_gemma":0.00007404546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002854897,"about_ca_topic_score_gemma":0.00007008317,"domain_scores_codex":[0.9944577,0.001794584,0.000923955,0.0008865016,0.00148997,0.0004473272],"domain_scores_gemma":[0.9970378,0.001851862,0.0001693674,0.0003934352,0.0002790157,0.0002685424],"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":[0.00005313836,0.0002876486,0.0008490332,0.00001278058,0.00004234428,0.00002484419,0.001049631,0.7590947,0.00001905592,0.000001381264,0.00005920758,0.2385063],"study_design_scores_gemma":[0.0004809122,0.003249633,0.00227971,0.00006717521,0.00002992663,0.00007626433,0.00657043,0.9823655,0.000006630891,0.00001454474,0.004687945,0.0001713423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.46723,0.0007888295,0.5294721,0.0001568789,0.001511327,0.000518487,0.00002149246,0.0002728275,0.00002806879],"genre_scores_gemma":[0.9951555,0.0001688565,0.00004962661,0.00001329385,0.0008075853,0.00004651692,0.000008019598,0.00004870543,0.003701889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5294225,"threshold_uncertainty_score":0.8927663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09340242677426551,"score_gpt":0.4280186097560809,"score_spread":0.3346161829818153,"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."}}