{"id":"W2952123902","doi":"10.48550/arxiv.1801.01301","title":"Sequential Decision Making with Limited Observation Capability: Application to Wireless Networks","year":2018,"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":"University of Waterloo","funders":"","keywords":"Lagrangian relaxation; Interval (graph theory); Index (typography); Mathematical optimization; State (computer science); Computation; Computer science; State space; Relaxation (psychology); Markov decision process; Decision maker; Function (biology); Bellman equation; Mathematics; Space (punctuation); Operations research; Algorithm; Markov process; 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":[0.002137015,0.0004396409,0.0005856728,0.000810516,0.0004118275,0.0004045262,0.002437835,0.0005047065,0.0001559487],"category_scores_gemma":[0.0008946834,0.0003990069,0.0001894241,0.003360561,0.0003574919,0.0005856795,0.002245135,0.0008262635,0.0003620475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007729356,"about_ca_system_score_gemma":0.0003073069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001263251,"about_ca_topic_score_gemma":0.0006797187,"domain_scores_codex":[0.9949226,0.0003941894,0.0006167132,0.002497931,0.0009403908,0.0006281188],"domain_scores_gemma":[0.9929562,0.001400076,0.0006030475,0.002564424,0.002153243,0.0003229632],"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":[0.0007480007,0.00007434975,0.01282136,0.00001295711,0.00004188156,0.00005683917,0.0001191307,0.9486247,0.00002917451,0.0007763018,0.0004556045,0.03623969],"study_design_scores_gemma":[0.000455582,0.0001482833,0.01407189,0.0001714833,0.00004503515,0.000003880907,0.0001800146,0.9293246,0.00007480515,0.05405102,0.0009794375,0.0004939793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4251719,0.000008556496,0.5734911,0.0000570623,0.0002770098,0.000753454,0.00002034775,0.00009483079,0.0001257225],"genre_scores_gemma":[0.990447,0.00002491574,0.008333908,0.0001086726,0.0003764347,0.00001164745,0.00005329983,0.00004836178,0.0005956877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5652751,"threshold_uncertainty_score":0.9998462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1943918856240933,"score_gpt":0.3173479699843214,"score_spread":0.1229560843602281,"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."}}