{"id":"W4320855027","doi":"10.48550/arxiv.2302.06548","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","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; Computer science; Noise (video); Focus (optics); Task (project management); Artificial intelligence; Margin (machine learning); Robot; Code (set theory); Machine learning; Deep learning; Pattern recognition (psychology); Set (abstract data type)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002174518,0.0002397737,0.0002472961,0.0003473179,0.0001898543,0.00008666673,0.0009976518,0.0001187001,0.00001993623],"category_scores_gemma":[0.00001470828,0.0002733936,0.00007951084,0.0008310211,0.00006008626,0.0003076021,0.001120898,0.0005837571,0.00008462328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000315158,"about_ca_system_score_gemma":0.000203833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001441306,"about_ca_topic_score_gemma":0.0002016868,"domain_scores_codex":[0.9984494,0.00006109721,0.0002194359,0.0008002387,0.0001045865,0.0003652744],"domain_scores_gemma":[0.9988749,0.00008515231,0.0002000503,0.0006827402,0.00005147434,0.0001057095],"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":[0.000003086731,0.00001916028,0.0004770942,0.00005132567,0.00002328222,0.0001849978,0.001063828,0.9788766,0.00001411726,0.01769094,0.00000360057,0.001591969],"study_design_scores_gemma":[0.0003011059,0.00004156662,0.004829536,0.0001947652,0.00001806582,0.000006738941,0.0004208559,0.986876,0.000004139647,0.006951937,0.00004172742,0.0003136364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1889179,0.00001219678,0.8096683,0.0001021524,0.0001083774,0.0002635707,0.000001093975,0.000413665,0.0005126643],"genre_scores_gemma":[0.986284,0.00005143359,0.01222268,0.00001794771,0.00001962586,0.00000994115,0.00002726173,0.00002077219,0.001346396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7974457,"threshold_uncertainty_score":0.9999718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0645443691250533,"score_gpt":0.1987499315039417,"score_spread":0.1342055623788884,"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."}}