{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00116318,0.0005031634,0.0005749387,0.0009073679,0.0004407441,0.0008009024,0.002176431,0.0004530737,0.0004739069],"category_scores_gemma":[0.0004036254,0.0004191701,0.0004111812,0.002002431,0.0004810685,0.0004673997,0.00364557,0.001345594,0.0007169849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005850625,"about_ca_system_score_gemma":0.0007724993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008734201,"about_ca_topic_score_gemma":0.001221643,"domain_scores_codex":[0.9950293,0.0003937551,0.0005727846,0.002347714,0.001024372,0.0006321043],"domain_scores_gemma":[0.995446,0.001240065,0.000323969,0.001952049,0.0007453622,0.0002925847],"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":[0.0003239754,0.0001095937,0.001657493,0.00002294318,0.0002167533,0.001277528,0.0001436866,0.9814504,0.0001113433,0.007457328,0.0008603495,0.006368625],"study_design_scores_gemma":[0.0007082699,0.0001234711,0.002438629,0.0004244893,0.000108071,0.00004256936,0.0008730644,0.4304192,0.0005692663,0.5625678,0.0008832715,0.0008419322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4107872,0.0002015767,0.5870069,0.0001175881,0.0006071992,0.0003648519,0.0000711835,0.0001515871,0.0006919246],"genre_scores_gemma":[0.9916701,0.00009807396,0.006196828,0.00007235805,0.0002013904,0.000004288693,0.00002095274,0.00005631689,0.001679708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5808828,"threshold_uncertainty_score":0.999826,"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."}}