{"id":"W3196395906","doi":"10.1109/jlt.2021.3107774","title":"Reinforcement Learning for Compensating Power Excursions in Amplified WDM Systems","year":2021,"lang":"en","type":"article","venue":"Journal of Lightwave Technology","topic":"Optical Network Technologies","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Agence Nationale de la Recherche","keywords":"Excursion; Reinforcement learning; Computer science; Wavelength-division multiplexing; Optical amplifier; Reduction (mathematics); Power (physics); Channel (broadcasting); Electronic engineering; Wavelength; Control theory (sociology); Engineering; Artificial intelligence; Telecommunications; Control (management); Optics; Physics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002970627,0.0001516686,0.0004496306,0.0005426361,0.00005529653,0.0000322385,0.0002611485,0.0003367856,0.00002042617],"category_scores_gemma":[0.0005847306,0.0001409378,0.0000921676,0.0005997191,0.00006769128,0.00009291076,0.00009479654,0.0008111434,0.000007343942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001753845,"about_ca_system_score_gemma":0.00003583089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.792379e-7,"about_ca_topic_score_gemma":0.000003475999,"domain_scores_codex":[0.9985899,0.00001954635,0.000734248,0.0001252313,0.0001523282,0.0003787026],"domain_scores_gemma":[0.9991106,0.0002280664,0.0001849911,0.0002160645,0.0002167054,0.00004351626],"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":[0.0000434685,0.00009921169,0.005041727,0.0002241088,0.000276958,0.0005538334,0.0002237768,0.7125168,0.06006383,0.211955,0.002703426,0.006297817],"study_design_scores_gemma":[0.009129023,0.003566626,0.002485967,0.004150025,0.0002592821,0.004127977,0.01975537,0.5886258,0.1433853,0.0354,0.186808,0.002306597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8933023,0.004256193,0.09379114,0.002277343,0.001503335,0.0003656587,0.000001375872,0.0008183309,0.003684353],"genre_scores_gemma":[0.9835881,0.000184478,0.01601974,0.00001400446,0.00005544072,0.00001498459,0.000001552536,0.00002920592,0.00009250751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1841046,"threshold_uncertainty_score":0.5747276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01325298880022795,"score_gpt":0.2376393046941039,"score_spread":0.2243863158938759,"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."}}