{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003567918,0.001306926,0.001331632,0.0004645335,0.0005600452,0.001850256,0.002125005,0.001471974,0.002102945],"category_scores_gemma":[0.02055376,0.0006717456,0.0005532868,0.0006564404,0.001561901,0.002994202,0.002057486,0.003152647,0.0004513433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001445118,"about_ca_system_score_gemma":0.001741955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002021875,"about_ca_topic_score_gemma":0.001939584,"domain_scores_codex":[0.9985385,0.0006407448,0.00008103625,0.0002863569,0.0002519112,0.0002015236],"domain_scores_gemma":[0.9882145,0.008973687,0.0008301738,0.001047427,0.0005702574,0.0003639525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003764666,0.0000807375,0.001366354,0.0001187692,0.00006937668,0.00006030943,0.0001030253,0.9164504,0.0009981652,0.03982396,0.001836959,0.03871549],"study_design_scores_gemma":[0.00002375102,0.0000359385,0.00006823188,0.00001150225,0.000009882945,0.00001485419,0.000009724974,0.9730622,0.0005131061,0.02596579,0.0002786767,0.000006269438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05612,0.0008659188,0.9378853,0.001201543,0.0001024589,0.00004669422,0.0001028144,0.0007740639,0.002901108],"genre_scores_gemma":[0.8950326,0.0003768986,0.1012105,0.0004069094,0.0001257208,0.0001018019,0.0001413836,0.000100587,0.002503671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003567918,"threshold_uncertainty_score":0.01886916,"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."}}