{"id":"W4295308610","doi":"10.1109/access.2022.3206035","title":"On Meeting a Maximum Delay Constraint Using Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Telefonaktiebolaget LM Ericsson","keywords":"Reinforcement learning; Computer science; Constraint (computer-aided design); Reinforcement; Mathematical optimization; Artificial intelligence; Mathematics; Engineering","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":[0.000769128,0.0002060656,0.0001956958,0.0002386577,0.0009747818,0.0005181695,0.00187419,0.0000381042,0.0001809258],"category_scores_gemma":[0.0001069575,0.0002225467,0.00008829019,0.0005777285,0.00004967258,0.0005971101,0.001166331,0.0006555068,0.00003398574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003343554,"about_ca_system_score_gemma":0.0001369443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008800697,"about_ca_topic_score_gemma":8.335467e-7,"domain_scores_codex":[0.9975454,0.0001997686,0.0004141956,0.0004562768,0.0008658175,0.0005185067],"domain_scores_gemma":[0.9987558,0.0002103239,0.0003362081,0.0005363154,0.00006886627,0.00009249783],"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":[0.000009313634,0.00001436172,0.0004743536,0.00001028559,0.00002323284,0.00005963385,0.0004238658,0.9906636,0.0005353972,0.005656942,0.0001961835,0.001932846],"study_design_scores_gemma":[0.0003825558,0.000221544,0.0000274807,0.00003353141,0.000008867919,0.00005197143,0.00009117066,0.9937512,0.001255014,0.0005241085,0.003367606,0.0002849044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05583293,0.00001551586,0.9300807,0.0001255691,0.001134202,0.0002429178,3.82008e-7,0.0002635207,0.01230429],"genre_scores_gemma":[0.9924831,0.000002563786,0.005860151,0.001151956,0.00006774222,0.00003231662,0.000003236459,0.00002298791,0.0003759024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9366502,"threshold_uncertainty_score":0.907519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04462453885572762,"score_gpt":0.3032042350847006,"score_spread":0.2585796962289729,"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."}}