{"id":"W4399426455","doi":"10.1109/access.2024.3411073","title":"Bounded Low Latency via Inverse Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Toronto","funders":"","keywords":"Bounded function; Computer science; Reinforcement learning; Latency (audio); Inverse; Artificial intelligence; Theoretical computer science; Mathematics; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001028357,0.001006312,0.0008712204,0.0003495916,0.0004675346,0.000944624,0.001235464,0.0007350357,0.001625271],"category_scores_gemma":[0.004407692,0.000382646,0.0003868336,0.0003591045,0.00102319,0.001328687,0.001182511,0.001515022,0.0002778182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101869,"about_ca_system_score_gemma":0.001706601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007364389,"about_ca_topic_score_gemma":0.005924185,"domain_scores_codex":[0.9994351,0.0001387647,0.00002526432,0.0001168066,0.0001625921,0.000121427],"domain_scores_gemma":[0.9979529,0.001313193,0.0002678258,0.0001415728,0.0002345731,0.0000898888],"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":[0.0000527425,0.00005135301,0.0004615477,0.00003773052,0.00001311454,0.00004510862,0.00003504283,0.9719715,0.001585347,0.005727504,0.0004911945,0.01952774],"study_design_scores_gemma":[0.000003331373,0.000009637911,0.00002117607,0.000001414448,0.000001432045,0.0000032528,0.000002221284,0.9982311,0.000149635,0.001509901,0.00006553311,0.0000012723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03208014,0.0002169399,0.9635028,0.0002899612,0.00004616336,0.00005180555,0.00003375858,0.0006044905,0.003173947],"genre_scores_gemma":[0.9498894,0.000137244,0.04785182,0.0001028882,0.00003255909,0.0001214394,0.00004485204,0.00006076334,0.001759033],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007364389,"threshold_uncertainty_score":0.01464307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02477077526986926,"score_gpt":0.2955000244589553,"score_spread":0.2707292491890861,"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."}}