{"id":"W4281383770","doi":"10.2200/s01170ed1v01y202202aim052","title":"Applying Reinforcement Learning on Real-World Data with Practical Examples in Python","year":2022,"lang":"en","type":"article","venue":"Synthesis lectures on artificial intelligence and machine learning","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ambrose University; Canadian Institute for Advanced Research","funders":"University of Manchester; University of Oxford","keywords":"Python (programming language); Computer science; Reinforcement learning; Real world data; Artificial intelligence; Data science; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009461107,0.0002861387,0.0003100854,0.0005115008,0.0006413523,0.0001425709,0.0002414584,0.00004164589,0.0006270376],"category_scores_gemma":[0.000619547,0.0002649128,0.00003409875,0.0005523727,0.00005670355,0.0001600387,0.000167995,0.001748546,0.0000420287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001258073,"about_ca_system_score_gemma":0.0000267108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006454182,"about_ca_topic_score_gemma":0.001462721,"domain_scores_codex":[0.9978069,0.0004005751,0.0004060025,0.0005212055,0.0004459223,0.0004194034],"domain_scores_gemma":[0.9982771,0.00115976,0.0001237929,0.0003353046,0.00001565378,0.00008838759],"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":[0.000227543,0.0000325032,0.001904497,0.00002302675,0.00002554074,0.0000313896,0.0005490163,0.8569046,0.0004126848,0.003348609,0.000027157,0.1365134],"study_design_scores_gemma":[0.00004937124,0.0003500853,0.0009423538,0.0000857472,0.00002299505,0.00001254444,0.001336109,0.9718793,0.002659221,0.000165318,0.02210948,0.0003874688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3953044,0.0006372556,0.5185876,0.004724464,0.001055296,0.004079102,0.00001245976,0.003858319,0.07174106],"genre_scores_gemma":[0.9984033,0.0001301867,0.0007238548,0.0001635601,0.0000912448,0.0001759466,0.00005861635,0.00007404305,0.0001792852],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6030988,"threshold_uncertainty_score":0.9999803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1123371378000468,"score_gpt":0.3250342094362956,"score_spread":0.2126970716362487,"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."}}