{"id":"W4210879300","doi":"10.1007/978-3-030-85053-1_12","title":"Learning COVID-19 Mitigation Strategies Using Reinforcement Learning","year":2021,"lang":"en","type":"book-chapter","venue":"Fields Institute communications","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Engineering; Medicine; Infectious disease (medical specialty); Structural engineering","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":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0008095486,0.0004458542,0.0007425993,0.0001580711,0.001788488,0.0001388381,0.0009827024,0.0006646062,0.0005986323],"category_scores_gemma":[0.008674748,0.0004555383,0.000310219,0.0001066816,0.0005610415,0.0002614286,0.001684559,0.002281124,0.00004350585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006576229,"about_ca_system_score_gemma":0.0008295746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004396048,"about_ca_topic_score_gemma":0.001273244,"domain_scores_codex":[0.9976464,0.0002734647,0.0009611823,0.0004625715,0.000333029,0.000323347],"domain_scores_gemma":[0.9936582,0.003362568,0.0007791869,0.001760286,0.0002760388,0.0001636894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005309078,0.00002190946,0.00007033142,0.0002688952,0.0002191034,0.00001256248,0.001063792,0.04316695,0.0000158162,0.9527819,0.001546819,0.0008266158],"study_design_scores_gemma":[0.00021045,0.0000704338,0.000006822609,0.000456627,0.0002134934,0.00001141554,0.0007921561,0.006530682,0.00000388364,0.205254,0.78596,0.0004901306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000224572,0.003155463,0.237624,0.007395776,0.000377481,0.0008405253,0.00001423394,0.0006726414,0.7496953],"genre_scores_gemma":[0.2580531,0.02361382,0.1091522,0.007657411,0.0008054392,0.0003489061,0.002171669,0.0002558104,0.5979416],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7844131,"threshold_uncertainty_score":0.9997897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4559772343083344,"score_gpt":0.4640591565083306,"score_spread":0.008081922199996205,"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."}}