{"id":"W6913045718","doi":"10.5555/3545946.3598862","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Open Repository and Bibliography (University of Luxembourg)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Noise (video); Focus (optics); Robot; Code (set theory); Training (meteorology); Transfer of learning; Deep learning","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":[0.001314276,0.0007869671,0.0008044404,0.0003092651,0.00029555,0.0005910683,0.001285494,0.0008635185,0.001809897],"category_scores_gemma":[0.005271661,0.0004450114,0.0003993214,0.0003390044,0.001076018,0.0009376835,0.001120107,0.001770873,0.0003907074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009185567,"about_ca_system_score_gemma":0.001360245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006143316,"about_ca_topic_score_gemma":0.007355419,"domain_scores_codex":[0.9995529,0.0001393431,0.00002413714,0.00009921308,0.0001213845,0.00006287325],"domain_scores_gemma":[0.9985588,0.0009102881,0.0001325128,0.0001535071,0.0001768102,0.00006807681],"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":[0.00008692899,0.00007557305,0.0007631996,0.00007897044,0.0000345391,0.00004458155,0.00005377459,0.9042712,0.002534724,0.01028422,0.001450953,0.08032132],"study_design_scores_gemma":[0.00001056397,0.00001712287,0.00003831072,0.00000510007,0.000002946485,0.000005264016,0.000002201056,0.9954045,0.0005640005,0.003686129,0.0002614849,0.000002431967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01603318,0.0002494446,0.9807176,0.0002215884,0.00003440672,0.00004144271,0.00005653031,0.001264096,0.001381627],"genre_scores_gemma":[0.7433433,0.0002292306,0.2527088,0.0002883625,0.00005405621,0.0002456456,0.0002511151,0.0002102183,0.002669273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006143316,"threshold_uncertainty_score":0.01221508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819754168377526,"score_gpt":0.2254355572201884,"score_spread":0.2072380155364131,"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."}}