{"id":"W6893880472","doi":"10.5281/zenodo.6521193","title":"Deep Reinforcement Learning for Optimal Experimental Design in Biology","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"European Commission","keywords":"Python (programming language); Reinforcement learning; Reinforcement; Directory; Learning classifier system; Optimal design","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":[0.004915383,0.0009963072,0.0009470031,0.0006684175,0.0004498883,0.00151089,0.002154635,0.001203581,0.03962586],"category_scores_gemma":[0.01698232,0.0009070426,0.0008238342,0.0007122373,0.001069074,0.002181697,0.002217585,0.003590663,0.01063052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001763672,"about_ca_system_score_gemma":0.002582995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001649457,"about_ca_topic_score_gemma":0.003133334,"domain_scores_codex":[0.9983374,0.0006800155,0.00008357074,0.0002674998,0.0005341653,0.00009737851],"domain_scores_gemma":[0.9942278,0.003606824,0.0003816141,0.000815511,0.0007108959,0.0002573705],"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":[0.0005409656,0.0001863894,0.002247046,0.001604451,0.0002380923,0.000149658,0.0001632962,0.2783868,0.01398579,0.2359698,0.225691,0.2408367],"study_design_scores_gemma":[0.0001367401,0.00006776352,0.0005060172,0.0001274166,0.00002829943,0.00004895975,0.00001528015,0.7323981,0.01476858,0.1938099,0.05804451,0.00004854761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001424637,0.0002556748,0.9781965,0.0007613026,0.000143278,0.000069809,0.002386355,0.01189155,0.004870931],"genre_scores_gemma":[0.06042189,0.0005894537,0.9149643,0.0009737448,0.0001435777,0.0009433189,0.005133057,0.008225322,0.008605296],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03962586,"threshold_uncertainty_score":0.1325617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03986787889746189,"score_gpt":0.2884779984801965,"score_spread":0.2486101195827346,"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."}}