{"id":"W4394780679","doi":"10.48550/arxiv.2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","year":2024,"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; Government of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Prior probability; Machine learning; Reinforcement learning; Artificial intelligence; Regret; Bayesian probability; Principle of maximum entropy; Posterior probability; Task (project management); Entropy (arrow of time); Engineering","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":[0.005476256,0.001308747,0.002163082,0.0004357107,0.0006084362,0.001450007,0.001985573,0.002383905,0.004664248],"category_scores_gemma":[0.02468234,0.0008380369,0.00091918,0.0005858995,0.002092659,0.002823418,0.001973899,0.003587966,0.0005033312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001661865,"about_ca_system_score_gemma":0.001802548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005226127,"about_ca_topic_score_gemma":0.003505497,"domain_scores_codex":[0.9971294,0.001553397,0.00009429948,0.0006494452,0.0002672691,0.0003063429],"domain_scores_gemma":[0.9659793,0.0294809,0.001763482,0.001135414,0.0006018435,0.001039057],"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":[0.0005335179,0.0002159997,0.001444551,0.0001385613,0.00009396553,0.0001862161,0.000224487,0.9354621,0.0006853048,0.04009205,0.0007875782,0.02013565],"study_design_scores_gemma":[0.00006411971,0.0000543555,0.0001688516,0.00001197285,0.000009799756,0.00001274082,0.00001761974,0.9705418,0.000266548,0.02860873,0.0002331599,0.00001019793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2040657,0.0005997331,0.7870665,0.002160009,0.00008380043,0.0001835372,0.000276033,0.0004295493,0.005135145],"genre_scores_gemma":[0.9364232,0.0002356474,0.05922543,0.0002559234,0.00007259631,0.0002345602,0.0002031082,0.00005288207,0.003296629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005476256,"threshold_uncertainty_score":0.02896154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3528595338418768,"score_gpt":0.360209135595926,"score_spread":0.00734960175404914,"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."}}