{"id":"W7124285129","doi":"10.65109/vyhj2561","title":"Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer","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":"Université de Montréal","funders":"","keywords":"Dual (grammatical number); Process (computing); Reinforcement learning; Computation; Multi-agent system","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":[0.003344911,0.001207155,0.002092744,0.0006552481,0.0005758162,0.001115831,0.002196593,0.001657279,0.001917755],"category_scores_gemma":[0.007566814,0.000664133,0.0006757987,0.0005588165,0.001324233,0.00172554,0.00220473,0.001992388,0.0003406797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001107026,"about_ca_system_score_gemma":0.00162175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004677656,"about_ca_topic_score_gemma":0.004023141,"domain_scores_codex":[0.9986507,0.0005093436,0.00008612174,0.0003351001,0.0002674498,0.0001513107],"domain_scores_gemma":[0.9962102,0.002092287,0.0003923684,0.0003107288,0.0007994767,0.0001948711],"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":[0.00008159249,0.00004933313,0.001011063,0.00005307285,0.00006140245,0.00006637137,0.00006393443,0.953172,0.0008388492,0.008776546,0.0006796308,0.03514628],"study_design_scores_gemma":[0.000004739575,0.00001308671,0.00003608951,0.000002498517,0.000003706175,0.000005853704,0.000002133116,0.9981072,0.0001246036,0.001614704,0.00008317416,0.000002221273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01558718,0.0002104583,0.9824938,0.0001993149,0.00004131207,0.00004603608,0.00002120136,0.0001819747,0.001218764],"genre_scores_gemma":[0.8335852,0.0001912073,0.1623212,0.0003487357,0.00009160888,0.0003025871,0.0001153277,0.00008976609,0.002954421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004677656,"threshold_uncertainty_score":0.01768976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009116201324229783,"score_gpt":0.2322789746532104,"score_spread":0.2231627733289806,"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."}}