{"id":"W4404342998","doi":"10.48550/arxiv.2410.23029","title":"Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning","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":"Fonds de recherche du Québec – Nature et technologies; Institut de Valorisation des Données","keywords":"Computer science; Artificial intelligence; Mathematical optimization; Mathematics","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":[0.00741981,0.0003845739,0.0006311575,0.001451035,0.0004620588,0.0005263821,0.0008679962,0.0004268954,0.00003931683],"category_scores_gemma":[0.005795124,0.0003558091,0.0001463242,0.00102548,0.0003189028,0.0003212943,0.003479328,0.00220002,0.00002744847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000214602,"about_ca_system_score_gemma":0.0001562346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004325436,"about_ca_topic_score_gemma":0.00007304913,"domain_scores_codex":[0.9955611,0.0009404921,0.0004983265,0.002017194,0.0004365743,0.0005462885],"domain_scores_gemma":[0.9854304,0.01309331,0.0003682991,0.0006396015,0.0002854899,0.0001829626],"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":[0.001247259,0.00004612645,0.03602935,0.0002049842,0.000104838,0.001261145,0.002379796,0.7844131,0.000005875679,0.005664194,0.0003032584,0.1683401],"study_design_scores_gemma":[0.0005761408,0.0000672892,0.006535707,0.0006398101,0.00003932961,0.000009038597,0.002814829,0.4673073,0.000007801405,0.5210835,0.0006023864,0.000316801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.423836,0.001350146,0.5736824,0.00002178864,0.0003348276,0.0004596077,0.00008523448,0.0000681637,0.0001618512],"genre_scores_gemma":[0.99472,0.0005062266,0.002860154,0.00001417764,0.000130944,0.000005472733,0.0000107423,0.00004936488,0.00170285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.570884,"threshold_uncertainty_score":0.9998894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1995701599587951,"score_gpt":0.3614654136731448,"score_spread":0.1618952537143497,"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."}}