{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002787314,0.0004293559,0.0005545061,0.001347114,0.0004344515,0.0008866566,0.002129198,0.0002644289,0.0003281709],"category_scores_gemma":[0.001258327,0.0002993893,0.00006941556,0.001540449,0.001023417,0.0007660939,0.0006823791,0.001471524,0.0001025911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003525377,"about_ca_system_score_gemma":0.0007134519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006036498,"about_ca_topic_score_gemma":0.0003094176,"domain_scores_codex":[0.9925017,0.00008192599,0.0007909642,0.001694105,0.00423067,0.0007006869],"domain_scores_gemma":[0.9952549,0.002065842,0.0005039021,0.001051848,0.0009692887,0.0001541693],"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":[0.00001610694,0.00002564662,0.0001640481,0.000006445524,0.000003603831,0.00007819309,0.00009440864,0.7703255,0.00005704554,0.0004178814,0.00004053736,0.2287706],"study_design_scores_gemma":[0.0004516638,0.0004292006,0.0005222321,0.000211019,0.000005644345,0.00005116641,0.000001515789,0.8527621,0.0004841783,0.110205,0.03421547,0.000660796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002322885,0.0001386942,0.99373,0.0002518958,0.0004319361,0.0003463218,0.00002490017,0.00007783053,0.004766122],"genre_scores_gemma":[0.06337418,0.00003132737,0.8595313,0.0005007825,0.001547974,0.00001344352,0.00009011082,0.0001151945,0.07479571],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2281098,"threshold_uncertainty_score":0.9999458,"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."}}