{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00123107,0.0007791763,0.001052335,0.0002559283,0.0004047081,0.0006820529,0.001075991,0.0008338606,0.001801976],"category_scores_gemma":[0.004775514,0.0004137243,0.0003182671,0.0002572334,0.001109042,0.0009132727,0.001349439,0.001569858,0.0002466967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008341256,"about_ca_system_score_gemma":0.001288202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003239088,"about_ca_topic_score_gemma":0.003173447,"domain_scores_codex":[0.9994905,0.0001768975,0.00002321978,0.0001095952,0.00009170211,0.0001079654],"domain_scores_gemma":[0.9978963,0.001298967,0.000273149,0.0001461662,0.0001998843,0.0001856011],"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":[0.00009980996,0.00005988744,0.0005005718,0.00005045145,0.00002752426,0.00005528033,0.00003804841,0.9732046,0.001116995,0.007103231,0.0007978111,0.01694573],"study_design_scores_gemma":[0.00001003536,0.00001523492,0.00004416698,0.00000238026,0.000002373338,0.000004499617,0.000003274087,0.9958321,0.0001285565,0.003829354,0.0001259695,0.000001971674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06269987,0.0004204109,0.9319949,0.0005837295,0.00008928277,0.00006710672,0.00005981621,0.0005326229,0.003552328],"genre_scores_gemma":[0.9702873,0.0001022036,0.02775816,0.0001189397,0.00002887286,0.0000868099,0.00004406509,0.00003673744,0.001536889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003239088,"threshold_uncertainty_score":0.006510615,"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."}}