{"id":"W2957302152","doi":"10.48550/arxiv.1907.05772","title":"Exploration by Optimisation in Partial Monitoring","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Observable; Bounded function; Minimax; Upper and lower bounds; Simple (philosophy); Matching (statistics); Action (physics); Degenerate energy levels; Mathematics; Outcome (game theory); Combinatorics; Mathematical optimization; Computer science; Discrete mathematics; Mathematical economics; Statistics; Physics; Mathematical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.001223048,0.0002318711,0.0003494899,0.0004570761,0.00009115757,0.0002116104,0.001138984,0.0003131121,0.0001623404],"category_scores_gemma":[0.0005913803,0.0002207594,0.000124337,0.001015403,0.00007166098,0.001077986,0.0009264612,0.0007034214,0.0005076308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004773861,"about_ca_system_score_gemma":0.0001476319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001575799,"about_ca_topic_score_gemma":0.00003888725,"domain_scores_codex":[0.9971491,0.0003390717,0.0004026687,0.001203649,0.0005380732,0.0003674396],"domain_scores_gemma":[0.9977641,0.0006436112,0.0003170311,0.0008253345,0.0003232062,0.0001267845],"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":[0.00007085557,0.00005161041,0.01571355,0.000007149711,0.000009991618,0.00004561054,0.000176957,0.9788988,0.0001765612,0.0001556722,0.0004832831,0.004209925],"study_design_scores_gemma":[0.000848387,0.00006532043,0.003426068,0.00008353499,0.00001478792,7.168787e-7,0.001389139,0.9392959,0.003015424,0.04894144,0.002410901,0.0005083657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5638228,0.00006179441,0.4341544,0.0001016236,0.0009267743,0.0004504369,0.00003471913,0.00005263921,0.0003947683],"genre_scores_gemma":[0.9948958,0.000195596,0.0003086067,0.000006824794,0.0001864456,0.000003193206,0.00004700001,0.00001269904,0.004343795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4338458,"threshold_uncertainty_score":0.9002306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.360109314960615,"score_gpt":0.3313054139223404,"score_spread":0.02880390103827463,"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."}}