{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009582213,0.0001609709,0.0005319765,0.0002927202,0.0002411157,0.000807128,0.0006266476,0.0000719775,0.0002030923],"category_scores_gemma":[0.002465798,0.0001057944,0.0001387781,0.001318159,0.00009106736,0.003850078,0.0001440607,0.0002807879,0.0002261277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002907975,"about_ca_system_score_gemma":0.0000825762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004304526,"about_ca_topic_score_gemma":4.654057e-7,"domain_scores_codex":[0.9960571,0.0001732497,0.00124358,0.0001967707,0.002032056,0.000297254],"domain_scores_gemma":[0.9975045,0.0003063678,0.0008733839,0.0002140787,0.0009306776,0.0001709946],"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":[0.0002163787,0.00006583078,0.004929533,0.001522601,0.0003633782,0.000004606045,0.02464338,0.7862515,0.002387578,0.001435708,0.01888719,0.1592923],"study_design_scores_gemma":[0.0003932033,0.0001290179,0.0006521727,0.0000243458,0.00004980342,0.00001160373,0.003532072,0.9333184,0.001992723,0.0001721317,0.05954936,0.0001751419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1584672,0.002903038,0.8177622,0.005096915,0.0009163996,0.001616635,0.0001010901,0.0006649833,0.01247156],"genre_scores_gemma":[0.9986326,0.000005126721,0.0001966844,0.0001972878,0.0001054594,0.00002776804,0.00001418343,0.000009164954,0.0008117356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8401654,"threshold_uncertainty_score":0.7783154,"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."}}