{"id":"W7115933686","doi":"10.1109/tmlcn.2025.3646125","title":"Explainable Multi-Agent Reinforcement Learning for Extended Reality Codec Adaptation","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Machine Learning in Communications and Networking","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"Mitacs; Telefonaktiebolaget LM Ericsson","keywords":"Reinforcement learning; Codec; Network packet; Overhead (engineering); Packet loss; Adaptation (eye); Decomposition; Wireless network","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":[0.001515452,0.0006986897,0.0005436274,0.0003055129,0.0004026013,0.0008074532,0.001639192,0.001163184,0.003236898],"category_scores_gemma":[0.007662263,0.0003530717,0.0004582533,0.0002548594,0.0009893554,0.001156303,0.001449641,0.001829433,0.0005223169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113513,"about_ca_system_score_gemma":0.001143377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004229428,"about_ca_topic_score_gemma":0.004798083,"domain_scores_codex":[0.9992141,0.0003205866,0.00003989496,0.0001510513,0.0001818511,0.00009252187],"domain_scores_gemma":[0.997855,0.001138862,0.0002103011,0.0003058859,0.0003654972,0.0001243996],"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":[0.00009275692,0.0000609661,0.0008127398,0.00004161843,0.00003071459,0.0001139474,0.0001501661,0.9139398,0.002426613,0.02798797,0.001285548,0.05305723],"study_design_scores_gemma":[0.000007484376,0.000009107542,0.00002666727,0.000002480118,0.000001889697,0.000006763995,0.000004107824,0.9957248,0.0003691993,0.003499782,0.0003449831,0.000002765825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01573411,0.00007704402,0.9812268,0.0002372752,0.00003111789,0.00005870005,0.00003147749,0.0008576288,0.001745863],"genre_scores_gemma":[0.7331814,0.00008342696,0.2630314,0.0002162627,0.00002793595,0.0002300906,0.0001095684,0.0001682278,0.002951707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004229428,"threshold_uncertainty_score":0.0108285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09524532098212235,"score_gpt":0.3653373903419221,"score_spread":0.2700920693597998,"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."}}