{"id":"W4416251251","doi":"10.1109/ijcnn64981.2025.11228644","title":"Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Scalability; Sample (material); Function (biology); Graph; Range (aeronautics); Sample complexity; Sampling (signal processing)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001954924,0.0009565293,0.0008350281,0.002087125,0.0007256573,0.001037644,0.002183298,0.0001855405,0.0004023419],"category_scores_gemma":[0.000217691,0.001041589,0.0004006939,0.003117971,0.000169544,0.0007613654,0.002013878,0.001497944,0.0001826438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002416429,"about_ca_system_score_gemma":0.001252129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003215521,"about_ca_topic_score_gemma":0.00008857121,"domain_scores_codex":[0.9920519,0.0004720285,0.00232102,0.001701192,0.001537786,0.001916066],"domain_scores_gemma":[0.9968648,0.0003280005,0.0005937073,0.0016437,0.0002246205,0.0003451885],"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":[0.0000478566,0.0002717735,0.01357067,0.0002550257,0.0001085872,0.00003954717,0.001559661,0.9511117,0.000158329,0.02697656,0.0005370868,0.005363252],"study_design_scores_gemma":[0.004420446,0.0001518935,0.0009688422,0.001214694,0.00007818704,5.870787e-7,0.0003046011,0.9875208,0.001386,0.0001217536,0.002883463,0.0009487397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001009565,0.0002267966,0.9633641,0.003035316,0.001533785,0.001540684,5.126176e-7,0.0003279713,0.02896125],"genre_scores_gemma":[0.7914082,0.00007583219,0.08786111,0.003426479,0.00003884285,0.0001012123,0.00001946429,0.00004596055,0.1170229],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.875503,"threshold_uncertainty_score":0.9999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04092963577479208,"score_gpt":0.2967428688077293,"score_spread":0.2558132330329372,"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."}}