{"id":"W3170243566","doi":"10.48550/arxiv.2106.06885","title":"Online Learning with Optimism and Delay","year":2021,"lang":"en","type":"preprint","venue":"OpenBU (Boston University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Optimism; Computer science; Benchmarking; Online learning; Perspective (graphical); Robustness (evolution); Optimism bias; Machine learning; Artificial intelligence; Psychology; Multimedia; Marketing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008270846,0.0003368715,0.0006263399,0.0009208757,0.0004230455,0.0006844656,0.001526731,0.0003042857,0.0007972174],"category_scores_gemma":[0.0007267238,0.0002900508,0.0001200642,0.001263099,0.0003659153,0.0006273664,0.004612237,0.001699699,0.00004824193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002080328,"about_ca_system_score_gemma":0.0005305358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002064591,"about_ca_topic_score_gemma":0.000424501,"domain_scores_codex":[0.9958466,0.0004653028,0.0002986546,0.001397211,0.001548808,0.0004434577],"domain_scores_gemma":[0.9968012,0.0007114645,0.0003173509,0.0009286727,0.0009090796,0.0003322248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001262816,0.0009109493,0.01384469,0.0001526859,0.0007759481,0.02194409,0.005866226,0.6416742,0.0004591772,0.0009260969,0.002473287,0.3097099],"study_design_scores_gemma":[0.005147835,0.0009866563,0.01375847,0.0008694061,0.0002675689,0.0004226369,0.0505167,0.06664244,0.0009416639,0.001488775,0.8561087,0.002849085],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8069931,0.0007243738,0.1622245,0.001427179,0.0004341323,0.0009130535,0.0001244486,0.00015459,0.02700461],"genre_scores_gemma":[0.5500834,0.001908304,0.09169285,0.000142519,0.0002291998,0.000003117336,0.000350369,0.0001143123,0.3554759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8536355,"threshold_uncertainty_score":0.9999552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09327714844652883,"score_gpt":0.3639999897224988,"score_spread":0.2707228412759699,"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."}}