{"id":"W4404520510","doi":"10.1109/tccn.2024.3502512","title":"LiveStream Meta-DAMS: Multipath Scheduler Using Hybrid Meta Reinforcement Learning for Live Video Streaming","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Computer science; Reinforcement learning; Multipath propagation; Video streaming; Live streaming; Computer network; Real-time computing; Multimedia; Artificial intelligence","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0007328932,0.000311401,0.0004280925,0.0002476233,0.001346133,0.0006099699,0.0005331093,0.00006340689,0.00003446898],"category_scores_gemma":[0.00001726807,0.0002815311,0.0004260361,0.0003813379,0.0001427547,0.000842331,0.00004626109,0.0005554477,0.00001007264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008582816,"about_ca_system_score_gemma":0.0001343109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001360641,"about_ca_topic_score_gemma":0.00004796515,"domain_scores_codex":[0.9980364,0.0003787725,0.0004570353,0.0005364411,0.000217681,0.0003736211],"domain_scores_gemma":[0.9962785,0.002519767,0.0001353734,0.0007011519,0.000235213,0.000130034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005376737,0.0004938816,0.00001050319,0.0002510914,0.01521995,0.00001920737,0.005559493,0.05479974,0.0006228942,0.003254959,0.00005492118,0.9196596],"study_design_scores_gemma":[0.0003330671,0.0002219733,0.000003330264,0.0003971598,0.004518663,0.00002218771,0.00064719,0.9876826,0.00198176,0.0004115633,0.003440087,0.0003403825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006664075,0.01131367,0.9861258,0.0004445815,0.0002948013,0.000613393,0.00001873986,0.0002331817,0.0002894567],"genre_scores_gemma":[0.9508273,0.004105188,0.04387698,0.0003295539,0.00007342859,0.000528243,0.00002296923,0.00003145207,0.0002048879],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9501609,"threshold_uncertainty_score":0.9999637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1721561370258281,"score_gpt":0.3761808339663166,"score_spread":0.2040246969404885,"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."}}