{"id":"W3098528340","doi":"","title":"Differentiable Meta-Learning of Bandit Policies.","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differentiable function; Meta learning (computer science); Computer science; Artificial intelligence; Mathematics; Economics","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":[0.003101356,0.0009985984,0.001570871,0.000663801,0.0003879648,0.001974091,0.001354432,0.001993394,0.003887188],"category_scores_gemma":[0.01687821,0.0006398204,0.0005792422,0.001010746,0.001204498,0.002091465,0.001103635,0.002570441,0.0008479632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001368952,"about_ca_system_score_gemma":0.0013475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003091142,"about_ca_topic_score_gemma":0.003226932,"domain_scores_codex":[0.9989588,0.0005692044,0.00006485004,0.0001493919,0.0001298916,0.0001277094],"domain_scores_gemma":[0.9934993,0.005175847,0.0004050232,0.0003710663,0.0003860382,0.0001626375],"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":[0.0001916312,0.00009751564,0.0007189784,0.000151881,0.000130534,0.00004917669,0.00006265099,0.8685507,0.0004827465,0.07687354,0.002443861,0.05024691],"study_design_scores_gemma":[0.00001223969,0.00001912809,0.00005290448,0.0000215884,0.00001169937,0.000007357871,0.000004961644,0.9766604,0.0001746656,0.02269429,0.0003370906,0.00000382138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02219945,0.002785869,0.966449,0.001004932,0.00016393,0.00004569318,0.0001149619,0.0003671073,0.006869022],"genre_scores_gemma":[0.885905,0.001532032,0.1029654,0.0004708396,0.0001891203,0.0001997888,0.0002536741,0.0001291082,0.008355042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003887188,"threshold_uncertainty_score":0.01640177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.230175592855734,"score_gpt":0.4086101303330043,"score_spread":0.1784345374772703,"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."}}