{"id":"W3185619002","doi":"10.48550/arxiv.2107.08114","title":"Decentralized Multi-Agent Reinforcement Learning for Task Offloading Under Uncertainty","year":2021,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Marl; Computer science; Robustness (evolution); Task (project management); Curse of dimensionality; Artificial intelligence; Machine learning; Distributed computing; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008875586,0.0007406188,0.0008183559,0.0002395438,0.0005277461,0.0007569962,0.002126041,0.0004811972,0.0001064899],"category_scores_gemma":[0.0006115683,0.0007788423,0.0005875722,0.0003689741,0.00009196931,0.0004043013,0.003361932,0.001438218,0.0001119773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008019626,"about_ca_system_score_gemma":0.0005982336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001535647,"about_ca_topic_score_gemma":0.00001648869,"domain_scores_codex":[0.995105,0.0002643708,0.001120847,0.001512385,0.0007875211,0.001209881],"domain_scores_gemma":[0.9962274,0.0003615195,0.000870203,0.001732978,0.0004828321,0.0003250938],"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":[0.00001619114,0.00004565586,0.01292575,0.0002384357,0.0002925723,0.00002034405,0.001241603,0.9824925,0.001039429,0.000793536,0.0002588542,0.0006351398],"study_design_scores_gemma":[0.00153857,0.0001343638,0.003875311,0.000456359,0.000103036,0.000006206993,0.0002874042,0.9831195,0.0009525014,0.00005086023,0.00857944,0.0008963919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06713107,0.0003857918,0.9271638,0.0005990381,0.002757818,0.001213738,0.000001655364,0.0005178554,0.0002291901],"genre_scores_gemma":[0.9419613,0.000453547,0.05149214,0.0008679179,0.0001967074,0.0002605464,0.0003273023,0.00008859766,0.004351903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8756717,"threshold_uncertainty_score":0.9994662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0788413178322847,"score_gpt":0.3097153766254181,"score_spread":0.2308740587931334,"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."}}