{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005048583,0.0001604715,0.0002858777,0.00621262,0.0004326386,0.0003055272,0.0009913952,0.00006565405,0.0000177558],"category_scores_gemma":[0.000001955143,0.0001745856,0.00007592766,0.01129118,0.0001310165,0.001330044,0.0007567343,0.0002260288,0.000005615483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001858846,"about_ca_system_score_gemma":0.00005457616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002393538,"about_ca_topic_score_gemma":0.00002597623,"domain_scores_codex":[0.99865,0.000108573,0.0002086241,0.0003746784,0.0003224785,0.0003356949],"domain_scores_gemma":[0.999146,0.00009763281,0.0002492249,0.0003361301,0.00005625244,0.000114785],"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":[0.00006647701,0.00003004756,0.08781791,0.0002217422,0.0001540936,0.0006246768,0.008967955,0.892328,0.001369053,0.0007933839,0.0001142991,0.007512337],"study_design_scores_gemma":[0.0009284406,0.0003403837,0.0852458,0.0003021306,0.00002556269,0.00004119382,0.004422266,0.9079936,0.00006557807,0.00005446688,0.0002998543,0.0002806946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4572378,0.00005836101,0.5303624,0.0001174625,0.0001267402,0.0005779728,2.946207e-7,0.0002684935,0.0112505],"genre_scores_gemma":[0.9860739,0.0002627001,0.01293197,0.0000143998,0.000006263182,0.000002290881,0.000005076889,0.000009629834,0.0006937985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5288361,"threshold_uncertainty_score":0.7119396,"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."}}