{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001160058,0.0006813553,0.0007643051,0.0001705921,0.000550112,0.0005846403,0.002110781,0.0003111645,0.00005711554],"category_scores_gemma":[0.0007280151,0.0005524209,0.0002043808,0.000318033,0.0002152556,0.0002947394,0.002108131,0.001775351,0.0000260029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003051995,"about_ca_system_score_gemma":0.0006726903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007991151,"about_ca_topic_score_gemma":0.00001570868,"domain_scores_codex":[0.9958769,0.0003854148,0.0006268133,0.001353231,0.0008233794,0.0009342514],"domain_scores_gemma":[0.9966576,0.0005491657,0.0006801737,0.001451153,0.0004517319,0.0002101759],"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":[0.00009828847,0.0000157563,0.0004973037,0.000103689,0.00007497393,0.00001661815,0.0001977063,0.9921311,0.000001463115,0.004985755,0.0002233092,0.001654033],"study_design_scores_gemma":[0.0007581731,0.0002073397,0.00003418044,0.0003734348,0.00006852602,0.00000287031,0.00001248973,0.9958859,0.00001157197,0.001704872,0.0002373646,0.000703254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001262848,0.00004243448,0.9844986,0.0005695151,0.0009306814,0.0009772542,3.487434e-7,0.001027732,0.0106906],"genre_scores_gemma":[0.6930586,0.000001639932,0.3052683,0.0003712368,0.0005197053,0.0001200029,0.00001196082,0.00005550872,0.0005930578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6917957,"threshold_uncertainty_score":0.9996927,"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."}}