{"id":"W3176432538","doi":"10.1609/aaai.v35i1.16087","title":"Towered Actor Critic For Handling Multiple Action Types In Reinforcement Learning For Drug Discovery","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Receptor Mechanisms and Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; University of Alberta","funders":"University of Alberta; FedDev Ontario; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Pipeline (software); Action (physics); Artificial intelligence; Drug discovery; Space (punctuation); Machine learning; Programming language; Bioinformatics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002782315,0.001199128,0.001051699,0.0005644132,0.0004924174,0.0008889545,0.001767767,0.001197383,0.004276417],"category_scores_gemma":[0.005963036,0.000485678,0.0007970253,0.0004932327,0.001185817,0.001095364,0.001110381,0.00252093,0.000658538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001585658,"about_ca_system_score_gemma":0.002100207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009524968,"about_ca_topic_score_gemma":0.01076349,"domain_scores_codex":[0.9990726,0.0003714529,0.00006235053,0.0001794919,0.0002231449,0.00009086998],"domain_scores_gemma":[0.9976279,0.001635767,0.000152189,0.0001668068,0.0002803841,0.0001368922],"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":[0.0001204657,0.00002855681,0.0004503326,0.00006226011,0.00004183484,0.00006882287,0.0000310475,0.9658343,0.001066976,0.008359973,0.001162078,0.02277329],"study_design_scores_gemma":[0.00001120909,0.00001941999,0.00002313266,0.000003571199,0.000005584012,0.000006743189,0.000001587846,0.9970072,0.0002961537,0.002281881,0.0003401235,0.000003486596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01187828,0.0004651573,0.9810488,0.0002620839,0.000120565,0.00006932431,0.0001008747,0.001717856,0.004336924],"genre_scores_gemma":[0.7359469,0.0003736355,0.2562863,0.0003687433,0.0001201639,0.000251992,0.0002966324,0.0002984444,0.00605714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009524968,"threshold_uncertainty_score":0.01893908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06874953863389731,"score_gpt":0.3136991647026755,"score_spread":0.2449496260687782,"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."}}