{"id":"W4286713636","doi":"10.48550/arxiv.2108.00892","title":"Indexability and Rollout Policy for Multi-State Partially Observable\\n Restless Bandits","year":2021,"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":"Polytechnique Montréal","funders":"","keywords":"Observable; Monte Carlo method; State (computer science); Index (typography); Mathematical optimization; Computation; Computer science; Mathematical economics; Mathematics; Algorithm; Physics; Statistics","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":[0.002550257,0.0004708272,0.0008779875,0.00063941,0.0004172559,0.0006093936,0.001859276,0.0004525516,0.0001052891],"category_scores_gemma":[0.005842712,0.0004629053,0.0003746287,0.001477447,0.0005561306,0.0006433796,0.003188183,0.0009081228,0.00004101913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004141709,"about_ca_system_score_gemma":0.001410364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006665835,"about_ca_topic_score_gemma":0.002352141,"domain_scores_codex":[0.9947946,0.000625056,0.0006556481,0.002511505,0.000585166,0.0008280281],"domain_scores_gemma":[0.993597,0.001898931,0.000477242,0.001985405,0.001514851,0.0005265456],"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":[0.001143518,0.0006748048,0.1351406,0.0003418316,0.0003633349,0.0009109341,0.001772671,0.8373627,0.0001650312,0.003179206,0.0007082432,0.01823713],"study_design_scores_gemma":[0.003339518,0.0001508039,0.1160013,0.0001297172,0.00007996247,0.000007628114,0.001112395,0.7352659,0.0006414716,0.1382339,0.003979573,0.001057874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5766072,0.0001318798,0.4213536,0.0002254593,0.0003629879,0.0008661606,0.0002720411,0.00006910878,0.0001115454],"genre_scores_gemma":[0.9866697,0.0003174295,0.003593971,0.00008243403,0.0001804785,0.00001033534,0.00004730879,0.00004274453,0.009055588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4177597,"threshold_uncertainty_score":0.9997823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4995689698780204,"score_gpt":0.375060370729575,"score_spread":0.1245085991484453,"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."}}