{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001661353,0.0009121443,0.001425294,0.0005029898,0.0004281742,0.000752128,0.001069792,0.001116536,0.002022922],"category_scores_gemma":[0.00602966,0.0004162044,0.0004596979,0.0005694637,0.001329065,0.001194639,0.0009430615,0.001531303,0.0002411125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00117303,"about_ca_system_score_gemma":0.001936972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008928043,"about_ca_topic_score_gemma":0.006709794,"domain_scores_codex":[0.999415,0.0002242862,0.00002494639,0.0001066755,0.0001181251,0.0001110341],"domain_scores_gemma":[0.995903,0.003250229,0.0002811851,0.00009518989,0.0003178029,0.0001526878],"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":[0.000029124,0.00002118531,0.0003031177,0.00002515179,0.00001134487,0.00002493905,0.00001515534,0.9884766,0.0002324175,0.004794629,0.0002842213,0.005782012],"study_design_scores_gemma":[0.000004853128,0.00001027575,0.00002385294,0.000002364384,0.000001847127,0.000002700565,0.000002123969,0.9979322,0.00005077672,0.001904576,0.00006305234,0.000001335206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0378845,0.0004425307,0.9575676,0.0005311138,0.00006105563,0.00005116883,0.00004873084,0.0002365635,0.00317672],"genre_scores_gemma":[0.9412704,0.0002846065,0.05574764,0.0002811572,0.00005358093,0.0001200221,0.00008096261,0.00006031544,0.002101318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008928043,"threshold_uncertainty_score":0.01775211,"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."}}