{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001574721,0.001202782,0.001788891,0.0005777486,0.0003960068,0.0008981135,0.001978047,0.001265683,0.001434207],"category_scores_gemma":[0.004221206,0.0008216653,0.0007037628,0.0005064047,0.001325091,0.001733002,0.001812019,0.00207249,0.0003222288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000948779,"about_ca_system_score_gemma":0.001279009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004054166,"about_ca_topic_score_gemma":0.004478658,"domain_scores_codex":[0.9993068,0.0002739279,0.00003115242,0.0001512272,0.0001551431,0.00008171971],"domain_scores_gemma":[0.9982159,0.00109203,0.0002093041,0.0001608135,0.00018398,0.0001379553],"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":[0.00004514104,0.00005729828,0.0007885734,0.00004756014,0.00004662433,0.00005592145,0.00004983624,0.9586877,0.001124274,0.008850578,0.0004439598,0.02980265],"study_design_scores_gemma":[0.000004028913,0.0000112189,0.00002488191,0.000002370157,0.000002522884,0.000004292684,0.000001796927,0.996727,0.0001141855,0.003035338,0.00007020317,0.000002086253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01484794,0.0001604193,0.9838234,0.0001366596,0.00001957957,0.00002999209,0.00002442243,0.0002516479,0.0007060667],"genre_scores_gemma":[0.8630785,0.0001597201,0.1346135,0.0002139616,0.00004032702,0.0001636723,0.00016081,0.0001085136,0.001461001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004054166,"threshold_uncertainty_score":0.008328021,"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."}}