{"id":"W3034360859","doi":"","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Feature (linguistics); Generative model; Generative grammar; Computer science; Artificial intelligence; Feature learning; Machine learning; Linguistics","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":[0.003308018,0.001193407,0.002376899,0.0009009144,0.0008772358,0.002618845,0.002012132,0.003482681,0.003506488],"category_scores_gemma":[0.02240344,0.001492067,0.001190802,0.001149865,0.002978219,0.004883218,0.003479902,0.003540602,0.0007141049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139996,"about_ca_system_score_gemma":0.001117548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003311217,"about_ca_topic_score_gemma":0.003261361,"domain_scores_codex":[0.9981852,0.001095964,0.00007826278,0.0002832776,0.0001976314,0.0001596122],"domain_scores_gemma":[0.9868059,0.01110559,0.0004432595,0.000933652,0.0004167691,0.0002948312],"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":[0.000173859,0.00007284684,0.0008870505,0.0001002419,0.00008995599,0.0001128479,0.0001867194,0.8067304,0.0007544821,0.1616021,0.001556422,0.02773298],"study_design_scores_gemma":[0.00001638923,0.00001171279,0.00004116561,0.000009151094,0.000007843156,0.00001189498,0.000008356005,0.9259093,0.0001260813,0.07371467,0.0001368922,0.000006503011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02793323,0.0003372102,0.968564,0.0007430987,0.00004697276,0.00002221182,0.00007770748,0.0004218732,0.001853629],"genre_scores_gemma":[0.8364969,0.0003533042,0.1561261,0.0003908229,0.0001525675,0.0001966646,0.0002653791,0.0003236437,0.005694756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003506488,"threshold_uncertainty_score":0.01749468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03676985648599293,"score_gpt":0.3016793059080322,"score_spread":0.2649094494220393,"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."}}