{"id":"W3057037158","doi":"10.1007/978-3-030-56150-5_4","title":"Extending Sliding-Step Importance Weighting from Supervised Learning to Reinforcement Learning","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Machine learning; Artificial intelligence; Weighting; Stochastic gradient descent; Robustness (evolution); Online machine learning; Supervised learning; Mathematical optimization; Algorithm; Semi-supervised learning; Mathematics; Artificial neural network","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","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001332132,0.0008820774,0.0009084367,0.0008326701,0.0009202861,0.001251096,0.003883063,0.0003140222,0.0001057843],"category_scores_gemma":[0.0006477139,0.000869111,0.0002322971,0.001099607,0.0001597881,0.0006844394,0.002935478,0.003079321,0.0002085614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004397818,"about_ca_system_score_gemma":0.000364484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001234876,"about_ca_topic_score_gemma":0.00002653575,"domain_scores_codex":[0.993397,0.0001217401,0.0009595229,0.00274331,0.001641647,0.001136776],"domain_scores_gemma":[0.9967695,0.0008003329,0.000570765,0.00110949,0.0002079496,0.0005418869],"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":[0.000008821134,0.000008803956,0.0009303107,0.00003503811,0.0000221858,0.000233321,0.00269678,0.4805615,0.0005749204,0.005416363,0.00001921728,0.5094928],"study_design_scores_gemma":[0.0003210503,0.0003486204,0.000126165,0.0006976458,0.00001168416,0.00002428074,0.000002340124,0.9831627,0.000606167,0.00530231,0.008350198,0.001046827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005056805,0.0004027937,0.9901444,0.001626795,0.001542298,0.0004064812,0.000001535788,0.0006574619,0.004712502],"genre_scores_gemma":[0.4000791,0.00004944024,0.5945619,0.002357137,0.001608526,0.00001707877,0.00002952614,0.0001041642,0.001193173],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.508446,"threshold_uncertainty_score":0.9997857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01447910791569336,"score_gpt":0.2424965017675249,"score_spread":0.2280173938518316,"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."}}