{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002914561,0.00114697,0.001402095,0.0005134419,0.0005595685,0.00139548,0.001180299,0.0011195,0.002045576],"category_scores_gemma":[0.009299178,0.0004888262,0.0006566966,0.001140107,0.001640103,0.0018911,0.001268025,0.002023006,0.0001811446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001594945,"about_ca_system_score_gemma":0.001233967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004546012,"about_ca_topic_score_gemma":0.002498292,"domain_scores_codex":[0.9986386,0.0006786487,0.00005614572,0.0002288469,0.0002303022,0.000167386],"domain_scores_gemma":[0.9910137,0.007479154,0.000702221,0.0002842839,0.0003014379,0.0002191776],"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":[0.000114656,0.00005055447,0.0004805602,0.00007378198,0.00003775019,0.000091956,0.00005868203,0.9392256,0.0005749158,0.04707185,0.0003687732,0.01185092],"study_design_scores_gemma":[0.000008813869,0.00002466012,0.00005695964,0.000004838974,0.000004832757,0.000009253052,0.000006888899,0.9814404,0.0001156124,0.01815956,0.0001643728,0.000003862904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04589368,0.0009292671,0.9479917,0.0005686114,0.00007109757,0.00005414108,0.00008325087,0.0001384402,0.004269705],"genre_scores_gemma":[0.9390818,0.001080462,0.05589117,0.0001195064,0.0001347919,0.0001264496,0.00008380314,0.00003855351,0.003443501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004546012,"threshold_uncertainty_score":0.01541388,"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."}}