{"id":"W2796264871","doi":"10.1007/978-3-319-89656-4_3","title":"A Novel Evaluation Methodology for Assessing Off-Policy Learning Methods in Contextual Bandits","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Robustness (evolution); Outcome (game theory); Observational study; Machine learning; Artificial intelligence; Evaluation function; Policy learning; Quality (philosophy)","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":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05228436,0.0005277657,0.001138877,0.004207607,0.0004541891,0.0008935766,0.002695445,0.0005960916,0.0002539378],"category_scores_gemma":[0.0671384,0.0004306938,0.0002030521,0.002097528,0.001859028,0.0009400331,0.001127719,0.001431392,0.00004132377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056278,"about_ca_system_score_gemma":0.002749755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004909739,"about_ca_topic_score_gemma":0.0002835125,"domain_scores_codex":[0.990051,0.00128264,0.001419758,0.002484955,0.003643401,0.001118297],"domain_scores_gemma":[0.9643184,0.0313217,0.0007911787,0.001009021,0.002371603,0.0001881136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002994944,0.00001710449,0.00002838354,0.000008076645,0.00000679287,0.000005049731,0.00104227,0.09321009,0.001047103,0.0004035408,0.00001311142,0.9041885],"study_design_scores_gemma":[0.0007603572,0.0001919392,0.0003181412,0.0001463178,0.000008047446,0.00003710992,0.000006390933,0.6559699,0.001379872,0.3365732,0.004244145,0.0003646448],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001532491,0.0005079332,0.9950686,0.0005874262,0.001520095,0.001164882,0.00001091773,0.00004171178,0.000945215],"genre_scores_gemma":[0.008648114,0.00001737052,0.988436,0.0003989863,0.001396873,0.00006241976,0.00001061625,0.0000528665,0.0009767778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9038239,"threshold_uncertainty_score":0.9998145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4237425212056544,"score_gpt":0.5813126106282402,"score_spread":0.1575700894225859,"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."}}