{"id":"W4388040498","doi":"10.1109/pimrc56721.2023.10294047","title":"Collaborative Deep Reinforcement Learning for Resource Optimization in Non-Terrestrial Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Satellite Communication Systems","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Research and Development; Fundamental Research Funds for the Central Universities; National Research Foundation","keywords":"Computer science; Reinforcement learning; Resource allocation; Satellite; Markov decision process; Throughput; Resource management (computing); Handover; User equipment; Low earth orbit; Wireless; Trajectory; Communications satellite; Real-time computing; Distributed computing; Computer network; Telecommunications; Base station; Artificial intelligence; Markov process; 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":[0.0003255465,0.00008638997,0.0001215029,0.0001411269,0.00005203789,0.00004280459,0.0001307686,0.00007312003,0.00002156927],"category_scores_gemma":[0.00005408647,0.00009254009,0.00002261555,0.0007815785,0.000008391393,0.00008123507,0.00003464686,0.0001060141,0.00002286873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008558596,"about_ca_system_score_gemma":0.000008075763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008927533,"about_ca_topic_score_gemma":0.00002522096,"domain_scores_codex":[0.9993124,0.00004549237,0.000283157,0.00009544377,0.00008239209,0.0001811401],"domain_scores_gemma":[0.9994726,0.0002322367,0.00003590125,0.0001960041,0.00003312886,0.00003019339],"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":[0.00001690836,0.000001500624,0.000129358,0.000009988048,0.00000996349,3.830194e-7,0.0007354354,0.9966402,0.00001926453,0.00003885343,0.0007088407,0.001689279],"study_design_scores_gemma":[0.0005736677,0.00001948747,0.0000805776,0.00002667858,0.000002067873,1.932993e-7,0.0009068585,0.9757168,0.00007029001,0.000002676526,0.02250326,0.0000974188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001669214,0.0002324839,0.9819886,0.00005173683,0.0002745003,0.000839418,3.215985e-7,0.0005173893,0.01442633],"genre_scores_gemma":[0.9959032,0.0003766408,0.002245034,0.00001716917,0.0001328948,0.0002677467,0.000211265,0.00003764317,0.0008083843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.994234,"threshold_uncertainty_score":0.3773675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0181614403463493,"score_gpt":0.2560217762307202,"score_spread":0.2378603358843709,"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."}}