{"id":"W4313484226","doi":"10.48550/arxiv.2301.00512","title":"On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Receptor Mechanisms and Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données","keywords":"Reinforcement learning; Partially observable Markov decision process; Markov decision process; Dosing; Computer science; Task (project management); Action (physics); Markov chain; Markov process; Artificial intelligence; Machine learning; Markov model; Medicine; Pharmacology; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002344473,0.000853023,0.001157343,0.0002568668,0.0003932873,0.0009915441,0.001099516,0.001324843,0.001784267],"category_scores_gemma":[0.006722454,0.0004529948,0.00058648,0.0003721614,0.001541967,0.001611104,0.001041402,0.002452805,0.0002100244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101896,"about_ca_system_score_gemma":0.002346858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006049322,"about_ca_topic_score_gemma":0.004076165,"domain_scores_codex":[0.9991912,0.0003108005,0.00004882717,0.0002138577,0.0001644331,0.00007094033],"domain_scores_gemma":[0.9953134,0.003621878,0.000432669,0.0002732035,0.0002131283,0.0001456382],"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":[0.00009589533,0.00005642124,0.0005090287,0.0001130845,0.0000443255,0.00008017958,0.00005722514,0.9370477,0.002158936,0.0219267,0.0006393357,0.03727132],"study_design_scores_gemma":[0.00002481537,0.00006350165,0.0001394552,0.00001314255,0.00001179421,0.00003057895,0.00001058344,0.9759387,0.0008375231,0.02224701,0.0006731552,0.000009806654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02264835,0.0006537755,0.9727327,0.001044883,0.00005404538,0.00004435886,0.00004947569,0.0003515762,0.002420945],"genre_scores_gemma":[0.8735024,0.0005761564,0.1231837,0.0004284135,0.00008279844,0.00008875524,0.00005893189,0.00007956317,0.001999337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006049322,"threshold_uncertainty_score":0.0123989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08451059916471947,"score_gpt":0.2244786114057911,"score_spread":0.1399680122410716,"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."}}