{"id":"W4286909580","doi":"10.48550/arxiv.2110.02879","title":"Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Age of Information Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; Stanford Engineering; Canadian Institute for Advanced Research; National Institutes of Health; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Reinforcement learning; Computer science; Task (project management); Class (philosophy); Function (biology); Reinforcement; Artificial intelligence; Markov decision process; Machine learning; Psychology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001132406,0.0002085372,0.0002053955,0.0002010214,0.00032945,0.0002191129,0.0004355324,0.0001516634,0.00001302267],"category_scores_gemma":[0.00003059154,0.0002420079,0.0001226759,0.0004429563,0.00003573297,0.0008126702,0.0003622978,0.0003325659,0.000007958938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002822282,"about_ca_system_score_gemma":0.0002253984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001146398,"about_ca_topic_score_gemma":0.00001957765,"domain_scores_codex":[0.9987252,0.00008589324,0.0002326514,0.0005916667,0.0001289118,0.0002356559],"domain_scores_gemma":[0.9983138,0.00005688241,0.0004427154,0.0005040661,0.0005989984,0.00008352113],"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":[0.00004326992,0.0000389592,0.0006213353,0.00003014982,0.00003727457,0.00001469316,0.0002436171,0.9462706,0.0001564512,0.05220828,0.00008365543,0.0002516898],"study_design_scores_gemma":[0.0005030475,0.0001449994,0.001506549,0.00008956059,0.00003468908,0.00001058095,0.00007581578,0.9943215,0.0008966753,0.001988869,0.0001136425,0.0003141129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2145826,0.00001089031,0.784095,0.0001149731,0.0001462793,0.0003622709,0.00000600027,0.0001964966,0.0004855655],"genre_scores_gemma":[0.9378594,0.00002508462,0.06107674,0.0001021374,0.00003146163,0.000007476897,0.0007508619,0.00001374161,0.0001331577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7232768,"threshold_uncertainty_score":0.9868797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0344896227468478,"score_gpt":0.1715801177877418,"score_spread":0.137090495040894,"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."}}