{"id":"W1564634725","doi":"10.1007/11776420_31","title":"Online Learning with Variable Stage Duration","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Stochastic game; Hindsight bias; Regret; Repeated game; Computer science; Minimax; Mathematical economics; Variable (mathematics); Duration (music); Term (time); Game theory; Mathematics; Machine learning; Psychology","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":[0.004011873,0.000848004,0.002093046,0.00056144,0.0006130113,0.001264503,0.003283954,0.001997315,0.01373746],"category_scores_gemma":[0.01308702,0.0008167331,0.000911062,0.001262485,0.00113305,0.005044631,0.002542355,0.002894764,0.001578311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009860467,"about_ca_system_score_gemma":0.00129517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001383204,"about_ca_topic_score_gemma":0.001899908,"domain_scores_codex":[0.9986731,0.0004941798,0.00007916262,0.0003189605,0.000218161,0.0002165458],"domain_scores_gemma":[0.9843776,0.01283277,0.0004097128,0.001523027,0.00047793,0.0003789384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001479693,0.0006920283,0.001925141,0.0003532341,0.0001271604,0.0001501268,0.0002006509,0.3704389,0.002328018,0.1980791,0.00960673,0.4146191],"study_design_scores_gemma":[0.0001126034,0.0001777369,0.0002522973,0.00002461243,0.00003476806,0.00003894682,0.00001398162,0.895521,0.0009192282,0.1013022,0.001587892,0.00001464398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03115441,0.0007100815,0.9611899,0.0005264779,0.0001282339,0.00007693574,0.000148862,0.0005940954,0.005471007],"genre_scores_gemma":[0.7549266,0.0007935175,0.2041131,0.0003714989,0.0005146406,0.0004271846,0.0004588738,0.0002184817,0.03817601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01373746,"threshold_uncertainty_score":0.04595643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04876706117297198,"score_gpt":0.3533309066974802,"score_spread":0.3045638455245082,"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."}}