{"id":"W2790331160","doi":"10.1109/iros.2018.8594018","title":"Synthesizing Neural Network Controllers with Probabilistic Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial neural network; Artificial intelligence; Benchmark (surveying); Dropout (neural networks); Curse of dimensionality; Probabilistic logic; Machine learning; Controller (irrigation)","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":[0.0009689803,0.0009484898,0.0007752661,0.0003794274,0.0002917473,0.0006797885,0.001032743,0.0009872899,0.001869123],"category_scores_gemma":[0.004182598,0.0006019251,0.0005353861,0.0003047899,0.0008940192,0.0008758757,0.001296986,0.001582859,0.0004056041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007903806,"about_ca_system_score_gemma":0.001273693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003240813,"about_ca_topic_score_gemma":0.003402723,"domain_scores_codex":[0.9996611,0.00007825295,0.00001954994,0.00009239781,0.0001065353,0.00004220383],"domain_scores_gemma":[0.9988816,0.0006892351,0.0001385913,0.0001293676,0.0001175173,0.00004356821],"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":[0.00002046958,0.00001539558,0.0001732263,0.00002386465,0.00001369329,0.00002061909,0.00001714305,0.9758892,0.001002828,0.004882019,0.0004039367,0.0175376],"study_design_scores_gemma":[0.000004103994,0.000008259101,0.00001108058,0.000001772565,0.000001175632,0.000003230414,0.00000110846,0.9979244,0.0002495609,0.001666953,0.0001269254,0.000001334419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008049778,0.00006832758,0.9899203,0.00011227,0.00002494731,0.00003927755,0.00002565223,0.0005400864,0.001219481],"genre_scores_gemma":[0.6881567,0.000109293,0.3085391,0.0001944999,0.00003723048,0.0003164035,0.0001535878,0.0002152672,0.002277817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003240813,"threshold_uncertainty_score":0.006443918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0187376026044746,"score_gpt":0.2489554853752059,"score_spread":0.2302178827707313,"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."}}