{"id":"W4315629633","doi":"10.1109/globecom48099.2022.10000980","title":"Federated Deep Reinforcement Learning for Task Scheduling in Heterogeneous Autonomous Robotic System","year":2022,"lang":"en","type":"article","venue":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Reinforcement learning; Computer science; Distributed computing; Queue; Scheduling (production processes); Queueing theory; Dynamic priority scheduling; Robot; Task (project management); Two-level scheduling; Fair-share scheduling; Job shop scheduling; Artificial intelligence; Real-time computing; Mathematical optimization; Computer network; Quality of service; 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":[0.001197634,0.0006688521,0.0009489688,0.0002619664,0.0004031419,0.0005914072,0.001033724,0.0008094604,0.001021729],"category_scores_gemma":[0.002375083,0.0003104113,0.0003161007,0.000312911,0.0008766764,0.0008157184,0.0008901492,0.001231384,0.0001319371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001328669,"about_ca_system_score_gemma":0.001788424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009043317,"about_ca_topic_score_gemma":0.006004398,"domain_scores_codex":[0.9995368,0.0001371801,0.00001920474,0.0001084603,0.00008264871,0.0001157863],"domain_scores_gemma":[0.9991189,0.0004603021,0.0001172396,0.00005885324,0.0001581768,0.0000866325],"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":[0.00005452313,0.00005221243,0.0003944625,0.00001892774,0.0000170248,0.00003181313,0.00002265574,0.984682,0.0006729782,0.001732854,0.0002857445,0.01203491],"study_design_scores_gemma":[0.000003997978,0.00001048478,0.00003039383,6.790203e-7,0.000001381007,0.000001616309,0.000002045952,0.999123,0.00008387613,0.0007108628,0.00003072812,9.288377e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1054156,0.0004544826,0.8907743,0.0004993696,0.00007882524,0.00005023537,0.00003979793,0.0005053567,0.00218207],"genre_scores_gemma":[0.9769504,0.00006521118,0.02164375,0.0001049941,0.00001731657,0.00003931097,0.00002946171,0.00001862868,0.001130889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009043317,"threshold_uncertainty_score":0.01798135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03608818262905673,"score_gpt":0.2768275039875015,"score_spread":0.2407393213584448,"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."}}