{"id":"W4388685754","doi":"10.48550/arxiv.2311.07565","title":"Exploration via linearly perturbed loss minimisation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Regret; Minimisation (clinical trials); Perturbation (astronomy); Mathematics; Mathematical optimization; Applied mathematics; Computer science; Linear programming; Simple (philosophy); Algorithm; Statistics; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002148235,0.001190376,0.001153827,0.0005458741,0.0004042479,0.001305233,0.001599881,0.001683568,0.004398778],"category_scores_gemma":[0.0130497,0.0005602596,0.0007133486,0.0005455961,0.00165187,0.001881948,0.003159166,0.002398579,0.001369282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008314228,"about_ca_system_score_gemma":0.001083435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001164427,"about_ca_topic_score_gemma":0.001313435,"domain_scores_codex":[0.9983082,0.0009440291,0.00006238024,0.0002438538,0.00030154,0.0001400252],"domain_scores_gemma":[0.9961241,0.002781537,0.0002834166,0.0004197768,0.0002255501,0.0001656247],"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":[0.0002521887,0.00005735284,0.0007259173,0.0001287179,0.00006950345,0.0001138869,0.0001080291,0.888068,0.002292569,0.05855302,0.002956344,0.04667449],"study_design_scores_gemma":[0.00002157346,0.00003710398,0.0000464531,0.00001754436,0.000005600357,0.00002219935,0.000007860349,0.9676759,0.0006647754,0.03069212,0.0008005209,0.000008253428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01142731,0.0003345778,0.9838979,0.0004465145,0.00004937553,0.00006167876,0.00009673329,0.0007201065,0.002965753],"genre_scores_gemma":[0.6033142,0.0003925802,0.3850459,0.0008017856,0.0001493584,0.0005656722,0.0004595555,0.0005852539,0.008685688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004398778,"threshold_uncertainty_score":0.01471543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4737798012038305,"score_gpt":0.3347368947070564,"score_spread":0.1390429064967741,"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."}}