{"id":"W4285217523","doi":"10.1007/978-3-031-79167-3","title":"Applying Reinforcement Learning on Real-World Data with Practical Examples in Python","year":2022,"lang":"en","type":"book","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Canadian Institute for Advanced Research","funders":"","keywords":"Python (programming language); Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Programming language","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":[0.0007461413,0.000720474,0.000554277,0.0004958995,0.0003598678,0.001158466,0.001774083,0.0006535072,0.04737193],"category_scores_gemma":[0.004894417,0.0005019997,0.0006068884,0.0008022151,0.0005377423,0.0015426,0.001692018,0.001586547,0.01153126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005144099,"about_ca_system_score_gemma":0.0007943344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002546716,"about_ca_topic_score_gemma":0.004715302,"domain_scores_codex":[0.9996485,0.00006943259,0.0000300402,0.0000654823,0.0001556229,0.00003092044],"domain_scores_gemma":[0.9988081,0.0007220053,0.00003804956,0.0002305254,0.0001571185,0.00004403723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001503219,0.0001326046,0.001179961,0.0007358609,0.00005963339,0.0003389182,0.0002022043,0.1789789,0.004821827,0.05376547,0.1384329,0.6212015],"study_design_scores_gemma":[0.00004409299,0.00002071093,0.0004612481,0.00008478454,0.00001225319,0.0002333077,0.00004082604,0.8452202,0.006542407,0.06745557,0.07986192,0.00002262904],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.005246978,0.0002109052,0.9239339,0.0004387567,0.0001577813,0.0001003897,0.001483911,0.03620021,0.03222715],"genre_scores_gemma":[0.07470069,0.0003822954,0.8883657,0.000233122,0.00004245337,0.000298161,0.002804419,0.005492083,0.02768109],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.04737193,"threshold_uncertainty_score":0.1584749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08124021256867234,"score_gpt":0.3267524595788233,"score_spread":0.2455122470101509,"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."}}