{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001384146,0.0007926165,0.001189282,0.00027458,0.0003710402,0.0006396378,0.00122305,0.0009222904,0.001208539],"category_scores_gemma":[0.003341804,0.0003965332,0.000346131,0.0002907357,0.0009495523,0.0008064847,0.001066364,0.001352703,0.0001389361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162852,"about_ca_system_score_gemma":0.001381379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01080525,"about_ca_topic_score_gemma":0.009147787,"domain_scores_codex":[0.9994454,0.0001722014,0.00002671132,0.0001147856,0.00009694866,0.0001439279],"domain_scores_gemma":[0.9983439,0.001073333,0.0001889061,0.00007999236,0.0001936629,0.0001202483],"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":[0.00005968492,0.00003966132,0.0004677618,0.0000264221,0.0000206896,0.00003910591,0.00002662923,0.9832652,0.0004524186,0.002486045,0.0003545042,0.01276184],"study_design_scores_gemma":[0.000003981363,0.00000793986,0.00002694314,0.000001093074,0.000001692324,0.000001724278,0.000001647578,0.9992871,0.00005364097,0.0005805168,0.00003287191,9.284145e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0717425,0.0006281525,0.923857,0.0004500074,0.00008787117,0.00004762424,0.00004405833,0.0004289662,0.002713777],"genre_scores_gemma":[0.9783159,0.0001155153,0.0200283,0.0001204707,0.00002372438,0.00005095271,0.00003657638,0.00001848524,0.001290135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01080525,"threshold_uncertainty_score":0.02148473,"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."}}